Graphics card firmware security detection method and device

Abstract

The present invention discloses a graphics card firmware security detection method and device. The method comprises obtaining attribute information of a computer device where the graphics card firmware is located; performing graphics card Flash chip read and write processing on the graphics card firmware based on the attribute information to obtain graphics card firmware physical address information; analyzing the graphics card firmware BIOS data structure based on the graphics card firmware physical address information to obtain graphics card BIOS image location information; performing a security detection on the graphics card firmware based on the graphics card BIOS image location information to obtain a graphics card firmware performance evaluation index set, wherein the graphics card firmware performance evaluation index set includes hardware performance evaluation indexes and display performance evaluation indexes. The graphics card firmware performance evaluation index set is processed to obtain a graphics card firmware security detection result. The present invention effectively implements security detection of graphics card firmware, ensuring that the graphics card firmware can operate safely and effectively throughout its entire life cycle, thereby protecting the security of the device and user data.

Description

Technical Field

[0001] The present invention relates to the field of network security technology, and in particular to a graphics card firmware security detection method and device. Background Art

[0002] With the continuous development of computer technology, various intelligent control systems and intelligent applications have become ubiquitous in our daily lives. Communication equipment is mostly composed of firmware such as hard disk firmware, graphics card firmware, and network equipment firmware.

[0003] In the cybersecurity field, attacks against firmware and hardware, such as hard drive firmware, graphics card firmware, and network devices, are on the rise. Attackers are increasingly targeting the firmware and device drivers of hardware components to gain elevated privileges and maintain persistence. Firmware security testing is the process of ensuring that firmware remains stable and secure in the face of various potential threats.

[0004] The security of graphics card firmware is crucial to the security of the entire system. The goal of graphics card firmware security testing is to ensure that the firmware is protected against various security threats throughout its lifecycle, thereby protecting the security of devices and user data. With the prevalence of the Internet of Things and smart devices, graphics card firmware security testing is becoming increasingly important, as graphics card firmware security not only affects device security but also potentially impacts user privacy and the security of the entire network. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a graphics card firmware security detection method and device, the method comprising obtaining attribute information of the computer device where the graphics card firmware is located; performing graphics card Flash chip read and write processing on the graphics card firmware based on the attribute information to obtain graphics card firmware physical address information; analyzing the graphics card firmware BIOS data structure based on the graphics card firmware physical address information to obtain graphics card BIOS image location information; performing security detection on the graphics card firmware based on the graphics card BIOS image location information to obtain a graphics card firmware performance evaluation index set, wherein the graphics card firmware performance evaluation index set includes hardware performance evaluation indexes and display performance evaluation indexes. The graphics card firmware performance evaluation index set is processed to obtain a graphics card firmware security detection result. The present invention effectively implements security detection of graphics card firmware, ensuring that the graphics card firmware can operate safely and effectively throughout its entire life cycle, thereby protecting the security of the device and user data.

[0006] In order to solve the above technical problems, a first aspect of an embodiment of the present invention discloses a graphics card firmware security detection method, the method comprising:

[0007] S1, performing security testing on the graphics card firmware to obtain a set of graphics card firmware performance evaluation indicators; the graphics card firmware performance evaluation indicator set includes hardware performance evaluation indicators and display performance evaluation indicators;

[0008] S2: Process the graphics card firmware performance evaluation indicator set to obtain a graphics card firmware security detection result.

[0009] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the security detection of the graphics card firmware to obtain a set of graphics card firmware performance evaluation indicators includes:

[0010] S11, obtaining attribute information of the computer device where the graphics card firmware is located;

[0011] S12, performing graphics card Flash chip reading and writing processing on the graphics card firmware according to the attribute information to obtain graphics card firmware physical address information;

[0012] S13, analyzing the BIOS data structure of the graphics card firmware according to the graphics card firmware physical address information to obtain graphics card BIOS image location information;

[0013] S14: Perform security detection on the graphics card firmware according to the graphics card BIOS image location information to obtain a set of graphics card firmware performance evaluation indicators.

[0014] As an optional implementation manner, in the first aspect of the embodiment of the present invention, performing security testing on the graphics card firmware based on the graphics card BIOS image location information to obtain a graphics card firmware performance evaluation index set includes:

[0015] S141, using a preset first detection model to perform hardware detection on the graphics card firmware to obtain hardware performance evaluation indicators; the hardware performance evaluation indicators include model information, temperature information, fan speed information, video memory information, core frequency information, memory frequency information, and graphics card usage information;

[0016] S142, using a preset second detection model, performing display detection on the graphics card firmware to obtain display performance evaluation indicators; the display performance evaluation indicators include line synchronization information, field synchronization information, graphics rendering performance, image quality information, smoothness information, and frame rate information.

[0017] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the processing of the graphics card firmware performance evaluation indicator set to obtain the graphics card firmware security detection result includes:

[0018] S21, processing the hardware performance evaluation index to obtain a hardware performance evaluation index judgment matrix A;

[0019] The expression of the hardware performance evaluation index judgment matrix A is:

[0020]

[0021] Where a ij is the correlation coefficient between the i-th element and the j-th element in the hardware performance evaluation index, i = 1, 2, ..., n, j = 1, 2, ..., n;

[0022] S22, processing the display performance evaluation index to obtain a display performance evaluation index judgment matrix B;

[0023] The expression of the display performance evaluation index judgment matrix B is:

[0024]

[0025] Where b kp To show the correlation coefficient between the kth element and the pth element in the performance evaluation index, k = 1, 2, ..., m, p = 1, 2, ..., m;

[0026] S23, processing the hardware performance evaluation index judgment matrix A and the display performance evaluation index judgment matrix B to obtain a graphics card firmware security detection result.

[0027] As an optional implementation manner, in the first aspect of the embodiment of the present invention, the processing of the hardware performance evaluation index judgment matrix A and the display performance evaluation index judgment matrix B to obtain a graphics card firmware security detection result includes:

[0028] S231, processing the hardware performance evaluation index judgment matrix A to obtain the hardware performance evaluation index weight w a ;

[0029] S232, processing the display performance evaluation index judgment matrix B to obtain the display performance evaluation index weight w b ;

[0030] S233, processing the graphics card firmware performance evaluation index set to obtain hardware performance evaluation index membership and display performance evaluation index membership;

[0031] S234, the hardware performance evaluation index weight w a and the hardware performance evaluation index membership to obtain a hardware performance evaluation result;

[0032] S235, weighting the display performance evaluation index w b and the display performance evaluation index membership to obtain a display performance evaluation result;

[0033] S236: Integrate the hardware performance evaluation result and the display performance evaluation result to obtain a graphics card firmware security detection result.

[0034] As an optional implementation, in the first aspect of the embodiment of the present invention, the hardware performance evaluation index judgment matrix A is processed to obtain the hardware performance evaluation index weight w a ,include:

[0035] S2311, processing the hardware performance evaluation index judgment matrix A to obtain a benefit matrix A′ of the matrix A;

[0036] The expression of the benefit matrix A′ is:

[0037]

[0038] Among them, f(a ij ) is the i-th row and j-th column element in the benefit matrix A′;

[0039] S2312, solving the benefit matrix A′ to obtain eigenvalues ​​λ1, λ2, …, λ n , and find the eigenvector e corresponding to the eigenvalue i , i=1,2,…,n;

[0040] S2313, for the characteristic vector e i Processing is performed to obtain the hardware performance evaluation index weight w a ;

[0041] The hardware performance evaluation index weight w a The expression is:

[0042] w a =[w a1 ,w a1 ,…,w an ]

[0043] where w ai w a The i-th element in w′ ai Normalized to [0,1], we get w ai .

[0044] As an optional implementation, in the first aspect of the embodiment of the present invention, the weight w of the hardware performance evaluation index is a and the hardware performance evaluation index membership, to obtain a hardware performance evaluation result, including:

[0045] Using the hardware performance evaluation model, the hardware performance evaluation index weight w a and the hardware performance evaluation index membership to obtain a hardware performance evaluation result S1;

[0046] The hardware performance evaluation model expression is:

[0047]

[0048] Among them, w aq is the weight vector w a =(w a1 ,w a2 ,...w an ) in the qth element, u q (x) is the qth element in the hardware performance evaluation index membership.

[0049] A second aspect of an embodiment of the present invention discloses a graphics card firmware security detection device, the device comprising:

[0050] An evaluation index acquisition module is used to perform security detection on the graphics card firmware to obtain a set of graphics card firmware performance evaluation indicators; the graphics card firmware performance evaluation indicator set includes hardware performance evaluation indicators and display performance evaluation indicators;

[0051] The security detection module is used to process the graphics card firmware performance evaluation index set to obtain a graphics card firmware security detection result.

[0052] As an optional implementation manner, in the second aspect of the embodiment of the present invention, the security detection of the graphics card firmware to obtain a set of graphics card firmware performance evaluation indicators includes:

[0053] S11, obtaining attribute information of the computer device where the graphics card firmware is located;

[0054] S12, performing graphics card Flash chip reading and writing processing on the graphics card firmware according to the attribute information to obtain graphics card firmware physical address information;

[0055] S13, analyzing the BIOS data structure of the graphics card firmware according to the graphics card firmware physical address information to obtain graphics card BIOS image location information;

[0056] S14: Perform security detection on the graphics card firmware according to the graphics card BIOS image location information to obtain a set of graphics card firmware performance evaluation indicators.

[0057] As an optional implementation, in the second aspect of the embodiment of the present invention, the security check of the graphics card firmware is performed based on the graphics card BIOS image location information to obtain a graphics card firmware performance evaluation index set, including:

[0058] S141, using a preset first detection model to perform hardware detection on the graphics card firmware to obtain hardware performance evaluation indicators; the hardware performance evaluation indicators include model information, temperature information, fan speed information, video memory information, core frequency information, memory frequency information, and graphics card usage information;

[0059] S142, using a preset second detection model, performing display detection on the graphics card firmware to obtain display performance evaluation indicators; the display performance evaluation indicators include line synchronization information, field synchronization information, graphics rendering performance, image quality information, smoothness information, and frame rate information.

[0060] As an optional implementation manner, in the second aspect of the embodiment of the present invention, the processing of the graphics card firmware performance evaluation indicator set to obtain the graphics card firmware security detection result includes:

[0061] S21, processing the hardware performance evaluation index to obtain a hardware performance evaluation index judgment matrix A;

[0062] The expression of the hardware performance evaluation index judgment matrix A is:

[0063]

[0064] Where a ij is the correlation coefficient between the i-th element and the j-th element in the hardware performance evaluation index, i = 1, 2, ..., n, j = 1, 2, ..., n;

[0065] S22, processing the display performance evaluation index to obtain a display performance evaluation index judgment matrix B;

[0066] The expression of the display performance evaluation index judgment matrix B is:

[0067]

[0068] Where b kp To show the correlation coefficient between the kth element and the pth element in the performance evaluation index, k = 1, 2, ..., m, p = 1, 2, ..., m;

[0069] S23, processing the hardware performance evaluation index judgment matrix A and the display performance evaluation index judgment matrix B to obtain a graphics card firmware security detection result.

[0070] As an optional implementation manner, in the second aspect of the embodiment of the present invention, the processing of the hardware performance evaluation index judgment matrix A and the display performance evaluation index judgment matrix B to obtain a graphics card firmware security detection result includes:

[0071] S231, processing the hardware performance evaluation index judgment matrix A to obtain the hardware performance evaluation index weight w a ;

[0072] S232, processing the display performance evaluation index judgment matrix B to obtain the display performance evaluation index weight w b ;

[0073] S233, processing the graphics card firmware performance evaluation index set to obtain hardware performance evaluation index membership and display performance evaluation index membership;

[0074] S234, the hardware performance evaluation index weight w a and the hardware performance evaluation index membership to obtain a hardware performance evaluation result;

[0075] S235, weighting the display performance evaluation index w b and the display performance evaluation index membership to obtain a display performance evaluation result;

[0076] S236: Integrate the hardware performance evaluation result and the display performance evaluation result to obtain a graphics card firmware security detection result.

[0077] As an optional implementation, in the second aspect of the embodiment of the present invention, the hardware performance evaluation index judgment matrix A is processed to obtain the hardware performance evaluation index weight w a ,include:

[0078] S2311, processing the hardware performance evaluation index judgment matrix A to obtain a benefit matrix A′ of the matrix A;

[0079] The expression of the benefit matrix A′ is:

[0080]

[0081] Among them, f(a ij ) is the i-th row and j-th column element in the benefit matrix A′;

[0082] S2312, solving the benefit matrix A′ to obtain eigenvalues ​​λ1, λ2, …, λ n , and find the eigenvector e corresponding to the eigenvalue i , i=1,2,…,n;

[0083] S2313, for the characteristic vector e i Processing is performed to obtain the hardware performance evaluation index weight w a ;

[0084] The hardware performance evaluation index weight w a The expression is:

[0085] w a =[w a1 ,w a1 ,…,w an ]

[0086] where w ai w a The i-th element in w′ ai Normalized to [0,1], we get w ai .

[0087] As an optional implementation, in the second aspect of the embodiment of the present invention, the weight w of the hardware performance evaluation index is a and the hardware performance evaluation index membership, to obtain a hardware performance evaluation result, including:

[0088] Using the hardware performance evaluation model, the hardware performance evaluation index weight w a and the hardware performance evaluation index membership to obtain a hardware performance evaluation result S1;

[0089] The hardware performance evaluation model expression is:

[0090]

[0091] Among them, w aq is the weight vector w a =(w a1 ,w a2 ,...w an ) in the qth element, u q (x) is the qth element in the hardware performance evaluation index membership.

[0092] A third aspect of the present invention discloses another graphics card firmware security detection device, the device comprising:

[0093] a memory storing executable program code;

[0094] a processor coupled to the memory;

[0095] The processor calls the executable program code stored in the memory to execute part or all of the steps in the graphics card firmware security detection method disclosed in the first aspect of the embodiment of the present invention.

[0096] A fourth aspect of the present invention discloses a computer-storable medium, which stores computer instructions. When the computer instructions are called, they are used to execute some or all of the steps in the graphics card firmware security detection method disclosed in the first aspect of an embodiment of the present invention.

[0097] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0098] This invention discloses a graphics card firmware security detection method and device. By processing a set of graphics card firmware performance evaluation indicators, the device obtains a graphics card firmware security detection result. This invention effectively implements graphics card firmware security detection, ensuring that graphics card firmware operates safely and effectively throughout its entire life cycle, thereby protecting the security of the device and user data. BRIEF DESCRIPTION OF THE DRAWINGS

[0099] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0100] Figure 1 This is a flowchart of a graphics card firmware security detection method disclosed in an embodiment of the present invention;

[0101] Figure 2 This is a flow chart of another graphics card firmware security detection method disclosed in an embodiment of the present invention;

[0102] Figure 3 This is a schematic diagram of the graphics card firmware detection process disclosed in an embodiment of the present invention;

[0103] Figure 4 This is a schematic diagram of the HOOK int 13h code disclosed in an embodiment of the present invention;

[0104] Figure 5 This is a schematic structural diagram of a graphics card firmware security detection device disclosed in an embodiment of the present invention;

[0105] Figure 6 It is a structural diagram of another graphics card firmware security detection device disclosed in an embodiment of the present invention. DETAILED DESCRIPTION

[0106] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0107] The terms "first," "second," and so on, in the description and claims of the present invention and the accompanying drawings are used to distinguish between different objects, not to describe a specific order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, apparatus, product, or device comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or device.

[0108] References herein to "embodiments" mean that a particular feature, structure, or characteristic described in connection with the embodiments may be included in at least one embodiment of the present invention. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it constitute a separate or alternative embodiment that is mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0109] The present invention discloses a method and device for security detection of graphics card firmware. The method comprises obtaining attribute information of a computer device where the graphics card firmware is located; performing graphics card Flash chip read and write processing on the graphics card firmware according to the attribute information to obtain the physical address information of the graphics card firmware; analyzing the BIOS data structure of the graphics card firmware according to the physical address information of the graphics card firmware to obtain the graphics card BIOS image location information; performing security detection on the graphics card firmware according to the graphics card BIOS image location information to obtain a graphics card firmware performance evaluation index set, wherein the graphics card firmware performance evaluation index set includes hardware performance evaluation indexes and display performance evaluation indexes. The graphics card firmware performance evaluation index set is processed to obtain a graphics card firmware security detection result. The present invention effectively implements security detection of graphics card firmware, ensuring that the graphics card firmware can work safely and effectively throughout its entire life cycle, thereby protecting the security of the device and user data. Detailed descriptions are given below.

[0110] Example 1

[0111] See also Figure 1 , Figure 1 This is a flow chart of a graphics card firmware security detection method disclosed in an embodiment of the present invention. Figure 1The graphics card firmware security detection method described is applied to the field of network security technology, and the embodiment of the present invention does not limit it. Figure 1 As shown, the graphics card firmware security detection method may include the following operations:

[0112] S1, performing security testing on the graphics card firmware to obtain a set of graphics card firmware performance evaluation indicators; the graphics card firmware performance evaluation indicator set includes hardware performance evaluation indicators and display performance evaluation indicators;

[0113] S2: Process the graphics card firmware performance evaluation indicator set to obtain a graphics card firmware security detection result.

[0114] Optionally, the performing security testing on the graphics card firmware to obtain a set of graphics card firmware performance evaluation indicators includes:

[0115] S11, obtaining attribute information of the computer device where the graphics card firmware is located;

[0116] S12, performing graphics card Flash chip reading and writing processing on the graphics card firmware according to the attribute information to obtain graphics card firmware physical address information;

[0117] S13, analyzing the BIOS data structure of the graphics card firmware according to the graphics card firmware physical address information to obtain graphics card BIOS image location information;

[0118] S14: Perform security detection on the graphics card firmware according to the graphics card BIOS image location information to obtain a set of graphics card firmware performance evaluation indicators.

[0119] Optionally, performing security testing on the graphics card firmware according to the graphics card BIOS image location information to obtain a graphics card firmware performance evaluation index set includes:

[0120] S141, using a preset first detection model to perform hardware detection on the graphics card firmware to obtain hardware performance evaluation indicators; the hardware performance evaluation indicators include model information, temperature information, fan speed information, video memory information, core frequency information, memory frequency information, and graphics card usage information;

[0121] Optionally, the preset first detection model is 3Dmark, etc. This embodiment uses a test program developed by the user to initialize the COM component library and set various parameters in accordance with the WMI usage specifications in the C language. After successfully connecting to the ROOT\CIMV2 namespace of WMI, the WMI security level is set, and then the WMI request is executed, the Win32_VideoController table is selected, and the corresponding information of the graphics card is retrieved according to the names of the various information that need to be obtained.

[0122] S142, using a preset second detection model, performing display detection on the graphics card firmware to obtain display performance evaluation indicators; the display performance evaluation indicators include line synchronization information, field synchronization information, graphics rendering performance, image quality information, smoothness information, and frame rate information.

[0123] Optionally, the preset second detection model is 3Dmark or a dedicated instrument test. This embodiment uses a user-developed test program, such as using DirectX technology as the underlying user interface to perform graphics rendering testing on a graphics card. The test server software is designed and runs on the Windows XP operating system, which only supports DirectX 9.0 at most. Therefore, this program module uses the Direct3D 9.0 interface related to color and drawing in DirectX 9.0 to implement specific image rendering. The source program needs to include the header file d3d9.h, and the Microsoft Direct3D SDK external link library file d3d9.lib must also be added to the project.

[0124] Optionally, the processing of the graphics card firmware performance evaluation indicator set to obtain a graphics card firmware security detection result includes:

[0125] S21, processing the hardware performance evaluation index to obtain a hardware performance evaluation index judgment matrix A;

[0126] Specifically, the hardware performance evaluation indicators are comprehensively evaluated, and the evaluation results of model information, temperature information, fan speed information, video memory information, core frequency information, memory frequency information and graphics card usage information are given, and normalized to a value between 0 and 1 to obtain the judgment matrix A;

[0127] The expression of the hardware performance evaluation index judgment matrix A is:

[0128]

[0129] Where a ij is the correlation coefficient between the i-th element and the j-th element in the hardware performance evaluation index, i = 1, 2, ..., n, j = 1, 2, ..., n;

[0130] S22, processing the display performance evaluation index to obtain a display performance evaluation index judgment matrix B;

[0131] Specifically, the display performance evaluation indicators are comprehensively evaluated to provide evaluation results of row synchronization information, field synchronization information, graphics rendering performance, image quality information, smoothness information, and frame rate information, and are normalized to values ​​between 0 and 1 to obtain a judgment matrix B.

[0132] The expression of the display performance evaluation index judgment matrix B is:

[0133]

[0134] Where b kp To show the correlation coefficient between the kth element and the pth element in the performance evaluation index, k = 1, 2, ..., m, p = 1, 2, ..., m;

[0135] S23, processing the hardware performance evaluation index judgment matrix A and the display performance evaluation index judgment matrix B to obtain a graphics card firmware security detection result.

[0136] Optionally, the processing of the hardware performance evaluation index judgment matrix A and the display performance evaluation index judgment matrix B to obtain a graphics card firmware security detection result includes:

[0137] S231, processing the hardware performance evaluation index judgment matrix A to obtain the hardware performance evaluation index weight w a ;

[0138] S232, processing the display performance evaluation index judgment matrix B to obtain the display performance evaluation index weight w b ;

[0139] Processing the display performance evaluation index judgment matrix B to obtain a benefit matrix B′ of the matrix B;

[0140] The expression of the benefit matrix B′ is:

[0141]

[0142] Among them, f(b ij ) is the i-th row and j-th column element in the benefit matrix B′, min{B} means finding the minimum value of the matrix B, and max{B} means finding the maximum value of the matrix B;

[0143] S2312, solving the benefit matrix B′ to obtain eigenvalues ​​λ′1, λ′2, …, λ′ n , and find the eigenvector e′ corresponding to the eigenvalue i , i=1,2,…,n;

[0144] S2313, the characteristic vector e′ i Processing is performed to obtain the display performance evaluation index weight w b ;

[0145] The display performance evaluation index weight w b The expression is:

[0146] w b =[w b1 ,w b1 ,…,w bn ]

[0147] where w bi w b The i-th element in w′ bi Normalized to [0,1], we get w bi .

[0148] S233, processing the graphics card firmware performance evaluation index set to obtain hardware performance evaluation index membership and display performance evaluation index membership;

[0149] The hardware performance evaluation index membership includes model information membership, temperature information membership, fan speed information membership, video memory information membership, core frequency information membership, memory frequency information membership and graphics card usage information membership;

[0150] The display performance evaluation index membership includes the line synchronization information membership, field synchronization information membership, graphics rendering performance membership, image quality information membership, smoothness information membership, and frame rate information membership;

[0151] S234, the hardware performance evaluation index weight w a and the hardware performance evaluation index membership to obtain a hardware performance evaluation result;

[0152] S235, weighting the display performance evaluation index w b and the display performance evaluation index membership to obtain a display performance evaluation result;

[0153] Using the display performance evaluation model, the display performance evaluation index weight w b and the display performance evaluation index membership, to obtain a display performance evaluation result S2;

[0154] The display performance evaluation model expression is:

[0155]

[0156] Among them, w au is the weight vector w b =(w b1 ,w b2 ,...w bn ) in the uth element, u u (x) is the u-th element in the display performance evaluation index membership.

[0157] S236, integrating the hardware performance evaluation result and the display performance evaluation result to obtain a graphics card firmware security detection result, including:

[0158] S=S1w1+S2w2

[0159] Among them, S is the graphics card firmware security detection result, w1 is the hardware performance evaluation result weight, w2 is the display performance evaluation result weight, w1+w2=1, w1 and w2 are set by the experiment;

[0160] Optionally, the hardware performance evaluation index judgment matrix A is processed to obtain the hardware performance evaluation index weight w a ,include:

[0161] S2311, processing the hardware performance evaluation index judgment matrix A to obtain a benefit matrix A′ of the matrix A;

[0162] The expression of the benefit matrix A′ is:

[0163]

[0164] Among them, f(a ij ) is the i-th row and j-th column element in the benefit matrix A′, min{A} means finding the minimum value of the matrix A, and max{A} means finding the maximum value of the matrix A;

[0165] S2312, solving the benefit matrix A′ to obtain eigenvalues ​​λ1, λ2, …, λ n , and find the eigenvector e corresponding to the eigenvalue i , i=1,2,…,n, n is the number of eigenvectors;

[0166] S2313, for the characteristic vector e i Processing is performed to obtain the hardware performance evaluation index weight w a ;

[0167] The hardware performance evaluation index weight w a The expression is:

[0168] w a =[w a1 ,w a1 ,…,w an ]

[0169] where w ai w a The i-th element in w′ ai Normalized to [0,1], we get w ai .

[0170] Optionally, the weight w of the hardware performance evaluation index a and the hardware performance evaluation index membership, to obtain a hardware performance evaluation result, including:

[0171] Using the hardware performance evaluation model, the hardware performance evaluation index weight w a and the hardware performance evaluation index membership to obtain a hardware performance evaluation result S1;

[0172] The hardware performance evaluation model expression is:

[0173]

[0174] Among them, w aq is the weight vector w a =(w a1 ,w a2 ,...w an ) in the qth element, u q (x) is the qth element in the hardware performance evaluation index membership.

[0175] Thus, the present invention discloses a graphics card firmware security detection method and apparatus. By processing a set of graphics card firmware performance evaluation indicators, the method and apparatus obtains graphics card firmware security detection results. This invention effectively implements graphics card firmware security detection, ensuring that graphics card firmware operates safely and effectively throughout its entire lifecycle, thereby protecting the security of devices and user data.

[0176] Example 2

[0177] In this embodiment, after obtaining the hardware performance evaluation index judgment matrix A and the display performance evaluation index judgment matrix B, feature extraction is performed on the matrix A to obtain the first parameter information;

[0178]

[0179] Among them, H2 is the first parameter information, L is the preset length, j=1,2,…,L,δ j are the singular values ​​of matrix A;

[0180] Perform feature extraction on matrix B to obtain second parameter information, including:

[0181] Convert the matrix B into a one-dimensional vector x(t) (extract the elements of each row and concatenate them to form a one-dimensional vector);

[0182] Calculate fuzzy parameter information;

[0183]

[0184] Among them, A x (θ, τ) is the fuzzy parameter information, t is the time variable, τ is the displacement variable, θ is the frequency variable corresponding to τ, and * indicates conjugation.

[0185] Performing Hadamard product calculation on the fuzzy parameter information and a preset kernel function to obtain second parameter information;

[0186] The Hadamard product calculation formula is:

[0187]

[0188] Among them, C x is the second parameter information, the integration range is -∞~∞, g(θ,τ) is the preset kernel function, a=0.001,β=50,u,t is the time variable, τ is the time shift variable, Ω is the frequency variable corresponding to u, θ is the frequency variable corresponding to τ;

[0189] Fusing the first parameter information and the second parameter information to obtain fused feature parameter information;

[0190] Obtain first parameter information X and second parameter information Y to be fused;

[0191] Performing feature projection on the cluster feature information X and the cluster feature information Y to obtain projected cluster feature information X' and projected cluster feature information Y';

[0192] Processing the projected cluster feature information X' and the projected cluster feature information Y' to obtain a projection vector a1 and a projection vector b1;

[0193] The cluster feature information X, the cluster feature information Y, the projection vector a1 and the projection vector b1 are processed to obtain fusion feature parameter information of the cluster feature information X and the cluster feature information Y.

[0194] The preset detection model is trained using the fusion feature parameter information to obtain an optimized detection model;

[0195] The default detection model is a convolutional long short-term memory (ConvLSTM) network combined with an LSTM network. ConvLSTM introduces convolution operations based on LSTM, improving its ability to process time series data.

[0196] Model structure

[0197] Convolutional Long Short-Term Memory (ConvLSTM): ConvLSTM can more effectively capture spatiotemporal features by introducing convolution operations into LSTM units. Its calculation formula is as follows:

[0198] Forget Gate:

[0199]

[0200] f t : Forget gate output, which controls the degree of information forgetting; σ: Sigmoid activation function, which compresses the output value between 0 and 1; W xf : Input data; x t : Input data at the current moment; W hf : The hidden state of the previous moment; h t-1 The convolution kernel weight associated with the forget gate. W cf :Unit status; c t-1 : The unit state at the previous moment, which stores the accumulation of past information. f : The bias term of the forget gate, which helps adjust the output of the forget gate.

[0201] Input Gate:

[0202]

[0203] i t : Input gate output, controlling the degree of introduction of new information; W xi : Input data x t The convolution kernel weight associated with the input gate; W hi : The hidden state of the previous moment; h t-1 The convolution kernel weight associated with the input gate; W ci :Cell status c t-1 The weight associated with the input gate; b i : Bias term for input gate.

[0204] Output gate:

[0205]

[0206] o t : Output gate output, controlling unit status; c t : How much information is passed to the hidden state; W xo : Input data; x t The convolution kernel weight associated with the output gate; W ho : The hidden state of the previous moment; h t-1 The convolution kernel weight associated with the output gate; W co :Cell status c t The weight associated with the output gate; b o : Bias term for the output gate.

[0207] Unit status update:

[0208]

[0209] c t : The unit state at the current moment; tanh: Hyperbolic tangent function, compressing the value between -1 and 1. W xc : Input data x t Convolution kernel weights associated with the cell state update. W hc : The hidden state of the previous moment; h t-1 Convolution kernel weights associated with unit state updates; b c : Bias term for unit state update.

[0210] Hide status update:

[0211]

[0212] h t : The hidden state at the current moment.

[0213] o t : The output of the output gate determines the cell state c t How much information is passed to the hidden state.

[0214] The optimized detection model is used to process the hardware performance evaluation index judgment matrix and the display performance evaluation index judgment matrix to be tested, and the graphics card firmware security detection results are obtained.

[0215] Example 3

[0216] See also Figure 2 , Figure 2 This is a flow chart of another graphics card firmware security detection method disclosed in an embodiment of the present invention. Figure 2 The graphics card firmware security detection method described is applied to the field of network security technology, and the embodiment of the present invention does not limit it. Figure 2 As shown, the graphics card firmware security detection method may include the following operations:

[0217] 1. Overall solution:

[0218] Graphics card firmware security detection is carried out by injecting customized executable code (file) (first detection model, second detection model) into the graphics card firmware of the target machine after obtaining administrator privileges. During the system startup process, the executable file is directly parsed, loaded into the memory and executed. After the target machine's main control code is executed, it triggers a reverse connection to the designated C&C server and receives instructions. The C&C server can push the upper-layer payload code to it, ultimately achieving security detection. The upper-layer payload code is encrypted and sent to the controlled end. The injection method of executable code supports two methods: physical contact burning and software injection on the target machine.

[0219] like Figure 2 The graphics card firmware executable code injection architecture is divided into four modules, namely the graphics card Flash chip reading and writing module, the BIOS image data structure reverse analysis module, the real mode custom code execution module, and the Windows operating system kernel security protection mechanism breakthrough module.

[0220] First, we deeply reverse-engineer the official driver and implement the mapping of virtual memory to physical memory in the driver, so that the process can access any physical address space, thereby injecting customized executable code (file) (first detection model, second detection model) into the graphics card firmware. Then, in order to ensure the safe and stable execution of the customized code, we study the reverse analysis method of the graphics card BIOS data structure, module composition, and module function, and inject specific code into the specific location of the graphics card BIOS image. Then, through the HOOK technology, the customized code has the ability to execute in memory. After the target machine's main control code is executed, it triggers a reverse connection to the specified C&C server and receives instructions. The C&C server can push the upper-layer load code to it, and finally achieve security detection.

[0221] It is necessary to elevate the rights of the target computer in advance, confirm key configuration information such as the target computer's operating system and graphics card firmware, and implement security testing of the target graphics card firmware in a safe and controllable environment under the conditions met.

[0222] Table 1 Graphics card firmware security detection hardware list

[0223] Serial number Device Name Function quantity Remark 1 buspirate 3.6 BIOS flasher 1 2 sf600 BIOS flasher 1

[0224] Figure 3 This is a schematic diagram of the graphics card firmware security detection process.

[0225] 2. Software design plan

[0226] (1) Graphics card Flash chip reading and writing technology design

[0227] To read and write the graphics card BIOS, you must first understand the mechanisms and methods for writing to it. In current Win32 protected-mode operating systems (Windows 2000 and later), the operating system kernel has undergone significant changes, leveraging the x86 CPU's 32-bit protected mode to implement complete process address space protection, significantly enhancing overall system security and stability. The operating system fully utilizes the fundamental security feature of the i386 CPU—process space protection. This ensures that each process can only access its own virtual address space; the mapping of the virtual address space to the physical address space is performed jointly by the operating system and the northbridge chip. Due to the operating system's protection, any process cannot access the physical address space of another process, cannot directly access the graphics card BIOS address space, and cannot interfere with the behavior of other processes.

[0228] For the Windows operating system, access to the underlying hardware is accomplished through the driver mechanism. Preliminary research has found that the official flash and backup tools provided by graphics card BIOS manufacturers also provide read and write functions in the form of drivers.

[0229] We then conducted an in-depth reverse engineering analysis of the internal mechanisms of the drivers included in these official programs and discovered that these drivers all utilize functions related to system hardware, memory pools, memory zones, and physical memory translation. These functions are all related to establishing a mapping between physical memory and virtual memory within the kernel. In other words, the mapping of virtual memory to physical memory is implemented within the driver, allowing processes to access any physical address space.

[0230] Furthermore, the official flashing programs provided by graphics card BIOS manufacturers support a wide range of Flash chips from various manufacturers (over 40 different chips). Therefore, based on the above approach, we will analyze their read and write mechanisms and utilize their official drivers to flash custom code. Both physical contact flashing and direct software operation on the target computer are supported.

[0231] Official drivers also have an advantage: all major antivirus and protection software manufacturers have added official drivers to the whitelist, making them highly universal.

[0232] (2) Reverse analysis, parsing, specification and composition design of graphics card BIOS data structure

[0233] To ensure the safe and stable execution of the customized code (first and second detection models), it is necessary to study the reverse analysis methods of the graphics card BIOS data structure, module composition, and module functions, and inject specific code into the specific location of the graphics card BIOS image. Using static and dynamic analysis tools such as IDA Pro and OllyDBG, analyze the data structure of the graphics card firmware and study its exploitable mechanisms;

[0234] Research and analyze the format, hardware architecture, protocol specifications, BIOS image data structure, and native firmware code functions of NVIDIA, ATI / AMD graphics card firmware. This includes but is not limited to the following reference protocols and specifications:

[0235] US National Standard NIST-SP800-147: BIOS Protection Guidelines

[0236] NIST-SP800-193: Platform Firmware Resiliency Guidelines

[0237] ACPI specification: ACPI_5_0_Errata_B

[0238] PCI Option ROM Specifications

[0239] PCI Local Bus Specification

[0240] PCI Configuration Space Specification

[0241] Unified Extensible Firmware Interface Specification

[0242] (3) Research on HOOK technology and code execution mechanism in real mode

[0243] Based on the reverse analysis, parsing, specification and composition of the graphics card BIOS data structure, it is also necessary to study the relevant technologies for custom code execution in real mode, so that the operating system can run in a specified manner and execute custom code during the primary startup process. The overall attack code design in the real mode stage is divided into three steps:

[0244] Code executed during the BIOS POST phase (HOOK IVT);

[0245] Windows kernel startup phase code;

[0246] Load function code execution (external CMD / download execution).

[0247] The specific process design is as follows:

[0248] When the BIOS boots up, it executes the entry function of the graphics card firmware's PCI Option ROM (also known as PCI Expansion ROM). The PCI entry function (address) is a variable specified in the PCI protocol, meaning that for peripherals that comply with the PCI specification, during the BIOS initialization phase, the CPU will execute the address of the firmware in these peripherals, also known as the "entry address." This "entry address" is usually primarily a jump instruction, which jumps to another executable code area to execute the code. Therefore, a script program first modifies the firmware's PCI Option ROM entry address, then jumps to the set area to execute real-mode code. After completing the necessary operations, it returns (jumps) to the original firmware entry address, i.e., the graphics card firmware initialization code, to execute the original firmware's initialization function.

[0249] When the code executes, it first hooks IVT 10h, starting from the BIOS POST phase, loading the MBR / VBR, booting Windows or other OS, loading the kernel, and continuing until OS boot is complete. It can hook interrupts 10h, 13h, 19h, and other interrupts. At this point, int 13h is not initialized, so 10h is executed first.

[0250] During the BIOS boot process, whenever a string is displayed, the graphics card's IVT is called. Since this is already hooked, the code is executed every time INT 10h is called. However, since INT 10h is initialized early and stops executing after Windows boots to a certain point, the hook needs to be passed to another interrupt vector.

[0251] By the time INT 13h executes, the BIOS has already completed most device initialization. Therefore, passing the hook from INT 10h to INT 13h ensures the availability of all functions and allows the code to retain CPU control when the OS subsequently loads the kernel file. Within INT 13h, the code monitors the loading of content and initiates the attack upon detecting the loading of the Windows kernel file. However, the hook transfer still needs to be performed at this point, as INT 13h is no longer called after the Windows operating system kernel begins loading. Figure 4 This is a schematic diagram of the HOOK int 13h code disclosed in an embodiment of the present invention.

[0252] (4) Research on Windows operating system kernel security protection mechanism

[0253] To enable direct memory execution of custom code within the graphics card firmware, the Windows kernel must be modified. By hooking certain real-mode interrupt services, the custom code is executed when these interrupt services are called during the operating system boot process, indirectly overwriting the operating system kernel or other critical data. The hooked PsGetCurrentProcess() function is loaded at the beginning of the Windows operating system kernel. It obtains the base address of Ntoskrnl and then gradually retrieves the exact addresses of related functions. This allows for more complex operations, such as reverse linking, to be performed step by step.

[0254] During execution, assembly code is written specifically for x86 / x64 systems. Finally, the payload code is executed by creating and calling a thread, using the KeDelayExecutionThread function. It's important to note that the execution delay parameter must be set. If the delay is too short, certain operating system functions will not be initialized, and the remote control payload code will fail to execute.

[0255] (5) Interface design

[0256] The interface design of graphics card firmware security detection is shown in the following table:

[0257] Table 2 Graphics card firmware security detection interface design

[0258]

[0259] The system interface of the graphics card firmware detection program is shown in the following table:

[0260] Table 3 Graphics card firmware detection program interface description

[0261]

[0262] Data design: Mainly for the underlying information data, including system BIOS mode settings (such as UEFI, Legacy), graphics card BIOS mode (hybrid, pure UEFI, Legacy), operating system system mode (such as UEFI or traditional MBR method).

[0263] Target machine graphics card firmware (BIOS) data: includes the number of graphics cards on the target machine, graphics card type, graphics card manufacturer, graphics card BIOS size, free space in the graphics card BIOS, etc. Also includes whether the target machine graphics card BIOS is write-protected.

[0264] Target machine operating system data: includes the target machine operating system version and current user permissions, such as administrator or ordinary user.

[0265] Payload data: This system provides basic functions for testing and carrying upper-layer applications, such as rebound CMD or encrypted data channels, allowing users to transfer executable files.

[0266] Thus, the present invention discloses a graphics card firmware security detection method and apparatus. By processing a set of graphics card firmware performance evaluation indicators, the method and apparatus obtains graphics card firmware security detection results. This invention effectively implements graphics card firmware security detection, ensuring that graphics card firmware operates safely and effectively throughout its entire lifecycle, thereby protecting the security of devices and user data.

[0267] Example 3

[0268] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of a graphics card firmware security detection device disclosed in an embodiment of the present invention. Figure 5 The graphics card firmware security detection device described is applied to the field of network security technology, and the embodiments of the present invention do not limit it. Figure 5 As shown, the graphics card firmware security detection device may include the following operations:

[0269] S301, an evaluation index acquisition module, configured to perform security testing on graphics card firmware to obtain a graphics card firmware performance evaluation index set; the graphics card firmware performance evaluation index set includes hardware performance evaluation indexes and display performance evaluation indexes;

[0270] S302, a security detection module is used to process the graphics card firmware performance evaluation indicator set to obtain a graphics card firmware security detection result.

[0271] Example 4

[0272] See also Figure 6 , Figure 6 This is a schematic diagram of the structure of another graphics card firmware security detection device disclosed in an embodiment of the present invention. Figure 6 The graphics card firmware security detection device described is applied to the field of network security technology, and the embodiments of the present invention do not limit it. Figure 6 As shown, the graphics card firmware security detection device may include the following operations:

[0273] A memory 401 storing executable program code;

[0274] a processor 402 coupled to the memory 401;

[0275] The processor 402 calls the executable program code stored in the memory 401 to execute the steps of the graphics card firmware security detection method described in the first and second embodiments.

[0276] Example 5

[0277] An embodiment of the present invention discloses a computer-readable storage medium storing a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the graphics card firmware security detection method described in the first and second embodiments.

[0278] The device embodiments described above are merely illustrative. Modules described as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., they may be located in one place or distributed across multiple network modules. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0279] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus the necessary general hardware platform, or of course, by means of hardware. Based on this understanding, the above technical solution, in essence, or the portion that contributes to the prior art, can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0280] Finally, it should be noted that the graphics card firmware security detection method and device disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used to illustrate the technical solutions of the present invention, rather than to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features therein may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A graphics card firmware security detection method, characterized in that: The method comprises: S1, performing security testing on the graphics card firmware to obtain a set of graphics card firmware performance evaluation indicators; the graphics card firmware performance evaluation indicator set includes hardware performance evaluation indicators and display performance evaluation indicators; S2, processing the graphics card firmware performance evaluation index set to obtain a graphics card firmware security detection result, including: S21, processing the hardware performance evaluation index to obtain a hardware performance evaluation index judgment matrix A; The expression of the hardware performance evaluation index judgment matrix A is: Where a ij is the correlation coefficient between the i-th element and the j-th element in the hardware performance evaluation index, i = 1, 2, ..., n, j = 1, 2, ..., n; S22, processing the display performance evaluation index to obtain a display performance evaluation index judgment matrix B; The expression of the display performance evaluation index judgment matrix B is: Where b kp To show the correlation coefficient between the kth element and the pth element in the performance evaluation index, k = 1, 2, ..., m, p = 1, 2, ..., m; S23, processing the hardware performance evaluation index judgment matrix A and the display performance evaluation index judgment matrix B to obtain a graphics card firmware security detection result, including: S231, processing the hardware performance evaluation index judgment matrix A to obtain the hardware performance evaluation index weight w a ,include: S2311, processing the hardware performance evaluation index judgment matrix A to obtain a benefit matrix A′ of the matrix A; The expression of the benefit matrix A′ is: Among them, f(a ij ) is the i-th row and j-th column element in the benefit matrix A′; S2312, solving the benefit matrix A′ to obtain eigenvalues ​​λ1, λ2, …, λ n , and find the eigenvector e corresponding to the eigenvalue i , i=1,2,…,n; S2313, for the characteristic vector e i Processing is performed to obtain the hardware performance evaluation index weight w a ; The hardware performance evaluation index weight w a The expression is: a =[w a1 ,w a1 ,…,w an ]; where w ai w a The i-th element in Will w a ' i Normalized to [0,1], we get w ai ; S232, processing the display performance evaluation index judgment matrix B to obtain the display performance evaluation index weight w b ; S233, processing the graphics card firmware performance evaluation index set to obtain hardware performance evaluation index membership and display performance evaluation index membership; S234, the hardware performance evaluation index weight w a and the hardware performance evaluation index membership, to obtain a hardware performance evaluation result, including: Using the hardware performance evaluation model, the hardware performance evaluation index weight w a and the hardware performance evaluation index membership to obtain a hardware performance evaluation result S1; The hardware performance evaluation model expression is: Among them, w aq is the weight vector w a =(w a1 ,w a2 ,...w an ) in the qth element, u q (x) is the qth element in the hardware performance evaluation index membership; S235, weighting the display performance evaluation index w b and the display performance evaluation index membership to obtain a display performance evaluation result; S236: Integrate the hardware performance evaluation result and the display performance evaluation result to obtain a graphics card firmware security detection result.

2. The graphics card firmware security detection method according to claim 1, characterized in that: The security detection of the graphics card firmware is performed to obtain a set of graphics card firmware performance evaluation indicators, including: S11, obtaining attribute information of the computer device where the graphics card firmware is located; S12, performing graphics card Flash chip reading and writing processing on the graphics card firmware according to the attribute information to obtain graphics card firmware physical address information; S13, analyzing the BIOS data structure of the graphics card firmware according to the graphics card firmware physical address information to obtain graphics card BIOS image location information; S14: Perform security detection on the graphics card firmware according to the graphics card BIOS image location information to obtain a set of graphics card firmware performance evaluation indicators.

3. The graphics card firmware security detection method according to claim 2, characterized in that: The step of performing security detection on the graphics card firmware according to the graphics card BIOS image location information to obtain a graphics card firmware performance evaluation index set includes: S141, using a preset first detection model to perform hardware detection on the graphics card firmware to obtain hardware performance evaluation indicators; the hardware performance evaluation indicators include model information, temperature information, fan speed information, video memory information, core frequency information, memory frequency information, and graphics card usage information; S142, using a preset second detection model, performing display detection on the graphics card firmware to obtain display performance evaluation indicators; the display performance evaluation indicators include line synchronization information, field synchronization information, graphics rendering performance, image quality information, smoothness information, and frame rate information.

4. A graphics card firmware security detection device, characterized in that: The device comprises: An evaluation index acquisition module is used to perform security detection on the graphics card firmware to obtain a set of graphics card firmware performance evaluation indicators; the graphics card firmware performance evaluation indicator set includes hardware performance evaluation indicators and display performance evaluation indicators; The security detection module is used to process the graphics card firmware performance evaluation index set to obtain a graphics card firmware security detection result, including: S21, processing the hardware performance evaluation index to obtain a hardware performance evaluation index judgment matrix A; The expression of the hardware performance evaluation index judgment matrix A is: Where a ij is the correlation coefficient between the i-th element and the j-th element in the hardware performance evaluation index, i = 1, 2, ..., n, j = 1, 2, ..., n; S22, processing the display performance evaluation index to obtain a display performance evaluation index judgment matrix B; The expression of the display performance evaluation index judgment matrix B is: Where b kp To show the correlation coefficient between the kth element and the pth element in the performance evaluation index, k = 1, 2, ..., m, p = 1, 2, ..., m; S23, processing the hardware performance evaluation index judgment matrix A and the display performance evaluation index judgment matrix B to obtain a graphics card firmware security detection result, including: S231, processing the hardware performance evaluation index judgment matrix A to obtain the hardware performance evaluation index weight w a ,include: S2311, processing the hardware performance evaluation index judgment matrix A to obtain a benefit matrix A′ of the matrix A; The expression of the benefit matrix A′ is: Among them, f(a ij ) is the i-th row and j-th column element in the benefit matrix A′; S2312, solving the benefit matrix A′ to obtain eigenvalues ​​λ1, λ2, …, λ n , and find the eigenvector e corresponding to the eigenvalue i , i=1,2,…,n; S2313, for the characteristic vector e i Processing is performed to obtain the hardware performance evaluation index weight w a ; The hardware performance evaluation index weight w a The expression is: a =[w a1 ,w a1 ,…,w an ], where w ai w a The i-th element in Will w a ' i Normalized to [0,1], we get w ai ; S232, processing the display performance evaluation index judgment matrix B to obtain the display performance evaluation index weight w b ; S233, processing the graphics card firmware performance evaluation index set to obtain hardware performance evaluation index membership and display performance evaluation index membership; S234, the hardware performance evaluation index weight w a and the hardware performance evaluation index membership, to obtain a hardware performance evaluation result, including: Using the hardware performance evaluation model, the hardware performance evaluation index weight w a and the hardware performance evaluation index membership to obtain a hardware performance evaluation result S1; The hardware performance evaluation model expression is: Among them, w aq is the weight vector w a =(w a1 ,w a2 ,...w an ) in the qth element, u q (x) is the qth element in the hardware performance evaluation index membership; S235, weighting the display performance evaluation index w b and the display performance evaluation index membership to obtain a display performance evaluation result; S236: Integrate the hardware performance evaluation result and the display performance evaluation result to obtain a graphics card firmware security detection result.

5. A graphics card firmware security detection device, characterized in that: The device comprises: a memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the graphics card firmware security detection method according to any one of claims 1 to 3.

6. A computer storable medium, characterized in that The computer storable medium stores computer instructions, and when the computer instructions are called, they are used to execute the graphics card firmware security detection method according to any one of claims 1 to 3.

Images