Digital signature generation and authentication system and method

Abstract

The invention discloses a digital signature generation and authentication system and method. The system comprises a first terminal and a second terminal, the first terminal comprises a first acquisition module for generating a first graphical interface, responding to a signature executed by a user on the first graphical interface, and acquiring first vector coordinate data signed on the first graphical interface; the second acquisition module is used for sampling facial features of the user; the data processing module is used for extracting a first secret key parameter from the first vector coordinate data, taking the facial feature as a second secret key parameter, and encrypting the first vector coordinate data through the first secret key parameter and the second secret key parameter to obtain secret key data; the storage module is used for storing key data; the communication module is used for transmitting the key data to a second terminal; the second terminal comprises a third acquisition module for verifying the facial features of the user; and the generation module verifies the facial features, decrypts the key data by using the second key parameter, and requests the first terminal to generate a digital copy to the second graphical interface.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of encryption authentication technology, in particular to a digital signature generation and authentication system. BACKGROUND

[0002] At present, the mainstream digital signature system in the market mainly adopts public key infrastructure (PKI) technology to realize signature generation and verification through asymmetric encryption algorithm. However, such system has obvious technical defects: first, pure cryptography protection is difficult to resist advanced persistent threat (APT) attack, and attackers can obtain the private key of the user through social engineering or malicious software; second, the traditional digital signature lacks binding with the user's biological characteristics, and cannot effectively verify whether the signature behavior is performed by the legal user himself, resulting in high risk of signature forgery; third, the signature data in the existing system is usually stored and transmitted in the form of vector coordinates, and once intercepted, the attacker can directly reuse these data to forge signature.

[0003] In order to improve security, some systems try to combine biometric identification technology with digital signature. For example, some technical solutions verify identity by collecting dynamic behavior characteristics (such as pen pressure, speed, etc.) of the user when signing. However, this method still has obvious shortcomings: on the one hand, dynamic behavior characteristics are easily affected by user state, device difference and other factors, and the recognition accuracy is unstable; on the other hand, these characteristic data are usually stored in plaintext or simple encrypted form, with limited security. Some other technologies try to combine facial recognition with digital signature, but most of them only use facial recognition as an independent identity verification link, and lack deep integration with signature data itself, which cannot fundamentally prevent signature data from being tampered or forged.

[0004] In addition, the protection of signature data in the prior art relies mainly on traditional encryption algorithms, and lacks innovative processing of data form. When the signature data exists in the form of original vector coordinates, even after encryption, if the decryption key is leaked, the attacker can still directly obtain the complete signature information, resulting in the collapse of the entire security system. At the same time, the existing system often directly uses the original signature data for comparison in the signature verification link, which not only increases the risk of data leakage, but also gives the attacker the opportunity to obtain sensitive information by analyzing the verification process.

[0005] Therefore, there is an urgent need for a digital signature generation and authentication system that can deeply integrate user biological characteristics and signature data, has high anti-forgery capability, and can effectively protect the security of original signature data, in order to solve the security risks existing in the prior art and meet the growing demand for security authentication. SUMMARY

[0006] In view of the above problems, the present application provides a digital signature generation and authentication system to improve the security of digital signature use.

[0007] The first aspect of the present application comprises a first terminal and a second terminal, the first terminal is a generating terminal, and the second terminal is an authenticating terminal; The first terminal comprises: A first obtaining module configured to generate a first graphical interface, obtain first vector coordinate data of a signature of a user on the first graphical interface in response to a signature performed by the user on the first graphical interface; A second obtaining module configured to sample facial features of the user; A data processing module configured to extract a typical value and an atypical value from the first vector coordinate data as first key parameters, extract feature points and non-feature points from the facial features as second key parameters, and perform encryption of the first vector coordinate data through the first key parameters and / or the second key parameters to obtain key data; A storage module configured to store the key data; A communication module configured to transmit the key data to the second terminal; The second terminal comprises: A third obtaining module configured to sample facial features of the user and extract the second key parameters to return to the first terminal for verification; A generating module configured to, after the facial features pass the verification, decrypt the key data through the first terminal using the first key parameters and / or the second key parameters and then generate a digital copy to the second graphical interface.

[0008] As a preferred mode, the typical value comprises coordinate points of a first preset type position of the signature, and the atypical value comprises a preset number of other coordinate points selected from the path of the signature in addition to the typical value.

[0009] As a preferred mode, the feature points comprise pixel points of a second preset type position of the facial features, and the non-feature points comprise randomly selected pixel points in the facial features.

[0010] As a preferred mode, the first obtaining module is configured to: When generating the first graphical interface, adjust the interface display area so that the signature is located at the center position of the first graphical interface; Store original vector coordinates of the signature when the first graphical interface is generated, and store coordinate transformation values of the typical value and the atypical value when the signature is located at the center position; Store the original vector coordinates and the coordinate transformation values as the first vector coordinate data.

[0011] As a preferred mode, the data processing module is configured to: convert the first vector coordinate data into a first pixel matrix; The signature is cut into multiple geometric parts by using a segmented preprocessing method, and the pixel coordinates of each geometric part are redistributed; The pixel coordinates of each geometric part are merged to obtain a pixel set, and different geometric serial numbers and coordinate values are recorded; The coordinate transformation value is used as part of the encrypted pixel matrix, wherein the coordinate transformation value includes the coordinate transformation value of the typical value and the atypical value; The geometric serial number, coordinate value and coordinate transformation value are written into the encrypted pixel matrix, and the redundant coordinate data in the first pixel matrix is deleted.

[0012] As a preferred mode, the data processing module is configured to: Generate noise pixels and their virtual coordinates at a preset proportion of the pixel set; The noise pixels are used as the confusion coordinate values of adjacent data of each geometric part; Generate a block image based on the confusion coordinate values, and obtain the position of the block image in the first pixel matrix coordinate system; Obtain the noise pixel coordinates at the boundary of the block image; Obtain the updated coordinate position of each pixel after writing into the block image, and update to the pixel set.

[0013] As a preferred mode, the data processing module is configured to: The pixel data of the facial features is preprocessed as part of the confusion data and written into the block image; Generate a second key parameter based on the confusion data; Perform pixel migration operation on the first pixel matrix by combining the second key parameter with the first key parameter to encrypt the first vector coordinate data.

[0014] As a preferred mode, the generation module is configured to: Scan the facial features of the user to be authenticated to obtain scan facial feature data; Compare the scan facial feature data with the facial features in the second key parameter to verify the validity and authenticity of the scan facial feature data; When the verification is passed, use the second key parameter to decrypt the key data; Generate a digital copy based on the decryption result, and verify its authenticity by comparing the digital copy with the signature data in the second graphical interface; The digital copy is a non-vector copy that has been decrypted and subjected to pixel migration.

[0015] As a preferred mode, the data processing module is configured to: record an offset value between a first position coordinate when the first terminal samples the user's facial features and a second position coordinate when the second terminal samples the user's facial features; use the offset value as an additional key parameter to participate in the encryption process of the first vector coordinate data together with the first key parameter and the second key parameter; the additional key parameter is stored in the key data in an encrypted form.

[0016] In a second aspect of the present application, a digital signature generation and authentication method is provided, comprising the following steps: At the first terminal, a first graphical interface is generated, and a first vector coordinate data of a signature performed by a user on the first graphical interface is obtained in response to the signature; At the first terminal, the facial features of the user are sampled; Typical values and atypical values are extracted from the first vector coordinate data as first key parameters; feature points and non-feature points are extracted from the facial features as second key parameters; The first vector coordinate data is encrypted by the first key parameters and the second key parameters to obtain key data; The key data is transmitted to a second terminal; At the second terminal, the facial features of the user are verified; The key data is decrypted using the second key parameters; A request is sent to the first terminal to generate a digital copy to a second graphical interface; The digital copy is a non-vector copy processed by decryption and pixel migration.

[0017] Compared with the prior art, the present application has the following beneficial effects: The vector coordinate data of the signature and the facial biometric features of the user are deeply bound in the present application. In the signature generation stage, the signature trajectory and the facial features of the user are collected simultaneously; in the authentication stage, the signature data and the real-time collected facial features must be verified simultaneously, effectively preventing the risk of signature being used by others.

[0018] The pixel migration technology is used to process the signature data in the present application, which converts the original vector coordinates into an encrypted pixel matrix. This process not only includes conventional encryption operations, but also realizes a fundamental change in data form through pixel migration guided by facial features, making it difficult for attackers to reverse deduce the original signature.

[0019] The digital copy generated in the authentication link is a non-vector copy which is decrypted and performs pixel migration, and is separated from the original vector coordinate system. This design fundamentally prevents the possibility of obtaining the original signature data through the authentication process. Even if the authentication terminal is attacked, the attacker cannot obtain the original signature information that can be used for forgery, achieving the security goal of authentication without leakage.

[0020] The present application uses feature points and non-feature points of facial features as dynamic confusion values, so that the encryption parameters generated each time the signature is generated are associated with the user's biological feature state at that time. Since facial features have subtle random changes, even if the same user signs multiple times, the generated encryption parameters are different, effectively preventing attacks based on fixed keys and improving the dynamic security of the system. BRIEF DESCRIPTION OF DRAWINGS

[0021] The present application will be further described with the help of the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present application. For ordinary skilled in the art, other drawings can be obtained without creative labor on the basis of the following drawings.

[0022] Figure 1 is a structural schematic diagram of the system provided by the embodiment of the present application. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present application will be described clearly and completely below with the help of the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by ordinary skilled in the art without creative labor are within the scope of protection of the present application.

[0024] The digital signature generation and authentication system of the present application, as shown in Figure 1 , includes a first terminal and a second terminal, wherein the first terminal is a generation terminal and the second terminal is an authentication terminal.

[0025] The first terminal includes a first acquisition module, a second acquisition module, a data processing module, a storage module and a communication module; the second terminal includes a third acquisition module and a generation module.

[0026] In the embodiment, the first acquisition module is configured to generate a first graphical interface and acquire and store vector coordinate data of a signature in response to a signature performed by a user on the first graphical interface. Specifically, the first acquisition module displays a blank canvas on the touch screen as the first graphical interface, and when the user performs a signature operation using a finger or a stylus, the system samples and captures a handwriting track, accurately records the coordinates and timestamps of each sampling point, and forms a sequence of original vector coordinate data. When generating the first graphical interface, the first acquisition module dynamically adjusts the interface display area to automatically center the signature at the center position of the first graphical interface, and stores the original vector coordinates of the signature when the first graphical interface is generated. At the same time, the system calculates coordinate transformation values of typical values and atypical values of the signature when the signature is located at the center position through a coordinate transformation algorithm, wherein the typical values include the coordinates of the starting point, the main turning point and the ending point of the signature, and the atypical values include other coordinate points selected in the signature path except the typical values; the coordinate transformation value specifically represents an offset vector between the original global coordinates and the local coordinates after the center alignment, for example, the offset of the starting point from the original coordinates (120, 80) to the center coordinates (256, 256) is (+136, +176). The first acquisition module stores the original vector coordinates and the coordinate transformation values as the first vector coordinate data, ensuring that the coordinate transformation values serve as the metadata basis for the subsequent encrypted pixel matrix.

[0027] The second acquisition module is configured to sample the facial features of the user and acquire feature points and non-feature points of the facial features. In the embodiment, the second acquisition module captures facial images of the user at a rate of thirty frames per second through a front camera, and accurately locates sixty-eight facial feature points including the key anatomical points of the inner end points of the eyebrows, the pupil center, the nose tip, the corners of the mouth and the jaw contour by using a facial key point detection algorithm based on deep learning; at the same time, two hundred non-feature points are uniformly selected from the facial images as random pixel points by using a pseudo-random number generator, and these non-feature points strictly avoid the feature areas (such as eyes or lips) and are distributed in the non-key areas such as cheeks and forehead. The feature points include pixel points at the second preset type positions of the facial features, and the non-feature points include randomly selected pixel points in the facial features, and the system assigns the feature points with a high brightness value (level 255) and the non-feature points with a medium brightness value (level 128), forming a facial feature data set with a hierarchical structure.

[0028] The data processing module is configured to extract the typical values and the atypical values from the first vector coordinate data as first key parameters, and extract the feature points and the non-feature points from the facial features as second key parameters, and perform encryption on the first vector coordinate data through the first key parameters and the second key parameters. The specific implementation is as follows: Firstly, the data processing module converts the first vector coordinate data into a first pixel matrix. The system maps the signature trajectory into a two-dimensional coordinate system of five hundred by five hundred pixels, sets the pixel resolution according to the density distribution of the original vector coordinate data, converts each sampling point coordinate into the corresponding pixel position, and forms an initial pixel matrix; in this matrix, the signature trajectory is represented by white pixels (level 255), the background is filled with black pixels (level 0), and the timestamp information is implicitly encoded through the pixel gray value gradient.

[0029] Secondly, the data processing module adopts a segmented preprocessing method to cut the signature into multiple geometric parts. The system dynamically divides the signature path into five continuous geometric parts based on the curvature variation characteristics of the typical value: the starting segment (from the starting point to the first major turning point), the first turning segment (the first major turning point to the middle segment), the middle segment (the smoothest area of the path), the second turning segment (the middle segment to the last major turning point), and the ending segment (the last major turning point to the ending point); for each geometric part, the system independently sets the local coordinate system origin as its starting point coordinate, and reassigns the global coordinates as local coordinates, for example, the global coordinate (120, 80) of the starting segment is remapped to the local coordinate (0, 0), eliminating the dependence on global coordinates.

[0030] Next, the data processing module performs merging processing on the pixel coordinates of each geometric part to obtain a pixel set, only recording different geometric sequence numbers and coordinate values. The system iterates through all geometric parts, identifies pixel points with the same local coordinate values and merges them into a single data item, each data item contains a geometric sequence number identifier (such as the starting segment marked as G1) and the corresponding local coordinate value (such as (50, 30)), while eliminating duplicate coordinates; this process achieves efficient indexing through a hash table, compressing the original vector data to forty percent of the original volume.

[0031] Subsequently, the data processing module integrates the coordinate transformation values as the core component of the encrypted pixel matrix. The coordinate transformation values include the offset vector set of the typical value and the atypical value, such as the offset of the starting point (+136, +176) and the average offset of the atypical value (+100, +150); the system writes the geometric sequence number, local coordinate value, and coordinate transformation value into the metadata area of the encrypted pixel matrix together, forming a three-dimensional data structure: the first dimension stores the geometric sequence number, the second dimension stores the local coordinate value, and the third dimension stores the coordinate transformation value, ensuring the strong binding relationship between the coordinate transformation value and the pixel set.

[0032] Then, the data processing module generates a pixel set. The pixel set is not a simple aggregation of the same coordinate values, but a structured data set constructed by segment preprocessing, containing complete mapping of geometric serial numbers, local coordinate values, and coordinate transformation values; the system deletes redundant global coordinate data in the first pixel matrix and only retains the core information of the pixel set, further compressing the data volume to 25% of the original volume.

[0033] Further, the data processing module generates noise pixels and their virtual coordinates at a preset proportion of the pixel set. The system sets the noise proportion to 15%, and defines the noise pixels as confused coordinate values of adjacent data of each geometric part: specifically at the boundary of the geometric parts (such as the junction area of the starting segment and the first turning segment), the transition points of the local coordinates of adjacent geometric parts are extracted to generate virtual coordinate points as confused coordinate values; for example, the middle point (202, 152) between the ending local coordinate (200, 150) of the starting segment and the starting local coordinate (205, 155) of the first turning segment is selected as the confused coordinate value to blur the boundary features.

[0034] The data processing module generates block images based on the confused coordinate values. The block images are composed of confused coordinate values, and each block image corresponds to a boundary area of a geometric part (such as the junction of the starting segment and the first turning segment), and its position is accurately positioned in the coordinate system of the first pixel matrix; the system calculates the coordinates of the noise pixels at the boundary of the block image, and takes these coordinates as the core elements of the confused data, for example, the upper left corner coordinate (180, 130) and the lower right corner coordinate (220, 170) of the block image.

[0035] Subsequently, the data processing module obtains the updated coordinate positions of each pixel after writing the block image. The system adjusts the pixel coordinates through a dynamic displacement algorithm, which combines the overall distribution characteristics of the facial features: first, the geometric center coordinates of the facial feature points are calculated, and then a displacement vector field is generated according to the density distribution of the feature points; for example, when the facial feature points are dense in the left half area, the displacement vector field is shifted to the left by 5%, so that the updated coordinate positions are dynamically associated with the facial feature data; the updated coordinate positions are written into the pixel set in real time to form a dynamic coordinate mapping during the encryption process.

[0036] Key, the data processing module pre-processes the pixel data of the facial features and writes it as part of the confused data into the block image. Specifically, the system converts the feature points and non-feature points of the facial features into standardized pixel vectors: eliminates light differences through histogram equalization, normalizes the scale to a uniform size using affine transformation, and generates facial feature pixel data with fixed dimensions; this data is directly embedded into the pixel filling layer of the block image as confused data, for example, replacing the noise pixel value at the boundary of the block image with the normalized facial feature pixel value (such as the nose tip brightness value 200), and deeply integrating with the confused coordinate values.

[0037] Based on the above confusion data, the data processing module generates a second key parameter. The second key parameter contains the structural description of the confusion data (such as the embedding position of the facial feature pixels), the pixel migration rule (such as the displacement vector field calculation formula), and the dynamic displacement algorithm (such as the feature point density weight coefficient), which is completely derived from the preprocessing result of the facial feature, ensuring that the second key parameter is strongly bound to the user's biological characteristics.

[0038] Finally, the data processing module performs a pixel migration operation on the first pixel matrix by combining the second key parameter with the first key parameter. The system performs coordinate rearrangement and pixel value permutation on the pixel set according to the confusion data in the second key parameter: first, inject the facial feature pixel data as a confusion factor into the migration process, for example, use the normalized coordinates (100, 120) of the nose tip point as a seed point to generate a random permutation sequence; then perform nonlinear coordinate rearrangement on the pixel set, so that the local coordinates (50, 30) of the geometric sequence G1 are migrated to the new position (180, 210); after migration, an encrypted pixel matrix is generated, which has completely left the original vector coordinate system and only retains the encrypted pixel set data, and the original vector coordinate information is permanently destroyed.

[0039] The storage module stores the encrypted key data in the hardware-level secure encryption area, and the communication module transmits the encrypted key data to the second terminal through a preset transmission protocol.

[0040] On the second terminal side, the third acquisition module receives the encrypted key data and samples the user's facial features. The generation module performs the following operations: First, scan the facial features of the user to be authenticated to obtain scan facial feature data. In this embodiment, the camera of the second terminal captures the user's real-time facial image with the same parameters, and extracts sixty-eight feature points and two hundred non-feature points consistent with the first terminal.

[0041] Then, compare the scan facial feature data with the facial features in the second key parameter to verify the validity and authenticity of the scan facial feature data. Validity verification includes checking image sharpness (through edge sharpness index), lighting conditions (through gray scale variance threshold), and completeness (through feature point coverage); authenticity verification uses multi-modal liveness detection technology, which confirms the real face through micro-expression analysis (detects blinking frequency) and depth perception (infrared 3D imaging).

[0042] When the verification passes, the second key parameter is authorized to decrypt the encrypted pixel matrix. The decryption process is the inverse operation of the encryption process, which specifically includes: re-computing the confusion data structure according to the scanned facial features, restoring the original geometric sequence number and local coordinate value of the pixel set through the inverse pixel migration operation, and then reconstructing the first vector coordinate data; but the reconstruction process strictly depends on the real-time facial features, and static data cannot complete the decryption.

[0043] Based on the decryption result, the generation module generates a digital copy and verifies its authenticity by comparing the digital copy with the signed data to be authenticated. The digital copy is a non-vector copy that has been decrypted and subjected to pixel migration, and is specifically implemented as follows: the decrypted pixel set is converted into a four-hundred-by-four-hundred pixel binary dot matrix image, where white pixels represent the signature track and black pixels represent the background; the digital copy has been permanently rearranged in pixel position due to the confusion data of facial features injected in the pixel migration operation, and has no direct geometric mapping relationship with the original signature. For example, the starting point (120, 80) in the original signature is represented as a discrete pixel point (180, 210) in the copy, but this mapping depends on the real-time facial features (such as the coordinates of the tip of the nose) during authentication, resulting in the copy being unable to be reverse-engineered to restore the original vector coordinate data. Even if an attacker obtains the copy, it cannot be mapped to the original signature through coordinate backtracking or image matching, thereby completely blocking the risk of replay attacks and data theft and providing much higher security than traditional vector signatures.

[0044] In this embodiment, the data processing module also records the offset value between the first position coordinate when the first terminal samples the user's facial features and the second position coordinate when the second terminal samples the user's facial features. This offset value is derived from the change in the position of the facial features in the image coordinate system during the two sampling processes, for example, the tip of the nose is offset from the first terminal coordinate (300, 200) to the second terminal coordinate (310, 195) due to the user's head tilt; the system takes this offset value as an additional key parameter, which participates in the encryption process of the first vector coordinate data together with the first key parameter and the second key parameter, and the additional key parameter is embedded in the key data in the form of an encryption hash, enabling the cross-terminal authentication to have dynamic anti-offset capability.

[0045] In one embodiment of the application, the user completes the signature operation on a tablet computer (first terminal), the first acquisition module ensures that the signature is located in the center of the interface and stores the coordinate transformation value, and the second acquisition module synchronously captures the facial features; the data processing module performs segmented preprocessing, cuts the signature into five geometric parts, records only the geometric serial number and local coordinate value after reassigning the coordinates of each geometric part, and integrates the coordinate transformation value to the metadata area of the encrypted pixel matrix. The facial feature pixel data is written into the block image as obfuscated data after normalization preprocessing, and the block image is composed of obfuscated coordinate values at the adjacent boundaries of the geometric parts (such as the middle point at the junction of the starting segment and the first turning segment), which is used to generate the second key parameter. The system generates an encryption key and transmits it to the authentication terminal (such as the authentication device at the bank counter) through a secure channel. When the user goes to the bank to conduct business, the second terminal scans his facial features, the third acquisition module verifies the facial features and calculates the coordinate offset value of the two sampling positions; after the generation module passes the verification, the second key parameter is used to decrypt the key data, but the generated digital copy is a non-vector dot matrix image that cannot be mapped back to the original signature: all pixel positions in the copy are dynamically rearranged by the facial features, for example, the continuous strokes of the original signature are represented as discrete pixel clusters in the copy, and the pixel distribution pattern dynamically changes with the facial features of each authentication. This design ensures that even if the copy is intercepted, attackers cannot reconstruct the original signature track, because the copy does not contain any original vector coordinate information, and there is no reversible mapping relationship between the pixel layout of the copy and the original signature, thereby providing security protection.

[0046] The foregoing description and accompanying drawings fully illustrate embodiments of this disclosure to enable those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, procedural, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terminology used in this application is for describing embodiments only and is not intended to limit the claims. As used in the description of embodiments and claims, the singular forms “a,” “an,” and “the” are intended to equally include the plural forms unless the context clearly indicates otherwise. Similarly, the term “and / or” as used in this application means including one or more of the associated listed items and all possible combinations thereof. Additionally, when used in this application, the term "comprise" and its variations "comprises" and / or "comprising" refer to the presence of stated features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Without further limitations, an element defined by the phrase "comprises a..." does not exclude the presence of other identical elements in the process, method, or apparatus that includes said element. In this document, each embodiment may focus on the differences from other embodiments, and similar or identical parts between embodiments can be referred to mutually. For methods, products, etc., disclosed in the embodiments, if they correspond to the method section disclosed in the embodiments, the relevant parts can be referred to the description of the method section.

[0047] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented using electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods for each specific application to achieve the described functions, but such implementation should not be considered beyond the scope of the embodiments of this disclosure. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the described devices, apparatuses, and units can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0048] The diagrams of the flow and block diagrams show the architecture, functionality, and operation of possible implementations of apparatuses, methods and computer program products according to embodiments of the present disclosure. In this regard, each block in the flow and block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logic functions. In some alternative implementations, the actions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession can in fact be executed substantially concurrently or the actions of a block can be performed in the reverse order, depending upon the functionality involved. These diagrams of the flow and block diagrams are also intended to include any connected data storage and data processing artifacts and structures that can affect the operation of the subject matter described. If warranted, specific data storage artifacts can be shown in a block diagram and / or a flow diagram and referred to in the accompanying text. Conversely, no indication of such data storage artifacts should not be construed to imply that such data storage is not a possible implementation. In some alternative implementations, the actions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession can in fact be executed substantially concurrently or the actions of a block can be performed in the reverse order, depending upon the functionality involved. The description of a flow or block diagram of a process, method, or computer program product should not be construed to mean that all of the actions or steps are required to be performed in the order presented, nor that they are performed at all.

Claims

1. A digital signature generation and authentication system, characterized by, The application relates to a key data generation method and device, and a key data verification method and device. The first terminal and the second terminal are included, the first terminal is a generation terminal, and the second terminal is an authentication terminal; The first terminal comprises: A first acquisition module configured to generate a first graphical interface, acquire first vector coordinate data of a signature on the first graphical interface in response to a signature performed by a user on the first graphical interface; A second acquisition module configured to sample facial features of the user; A data processing module configured to extract typical values and atypical values from the first vector coordinate data as first key parameters, extract feature points and non-feature points from the facial features as second key parameters, and perform encryption of the first vector coordinate data through the first key parameters and / or the second key parameters to obtain key data; A storage module configured to store the key data; A communication module configured to transmit the key data to the second terminal; The second terminal comprises: A third acquisition module configured to sample facial features of the user, and extract the second key parameters to return to the first terminal to perform verification; 2. The digital signature generation and authentication system of claim 1, wherein, A generation module configured to, after the facial feature verification passes, decrypt the key data through the first terminal using the first key parameters and / or the second key parameters, and then generate a digital copy to a second graphical interface.

3. The digital signature generation and authentication system of claim 1, wherein, The typical values include coordinate points of a first preset type position of the signature, and the atypical values include a preset number of other coordinate points selected from the signature path in addition to the typical values.

4. The digital signature generation and authentication system of claim 1, wherein, The feature points include pixel points of a second preset type position of the facial features, and the non-feature points include randomly selected pixel points in the facial features. The first acquisition module is configured to: When generating the first graphical interface, adjust the interface display area so that the signature is located at the center position of the first graphical interface; Store the original vector coordinates of the signature when the first graphical interface is generated, and store the coordinate transformation values of the typical values and the atypical values when the signature is located at the center position; 5. The digital signature generation and authentication system of claim 4, wherein, Store the original vector coordinates and the coordinate transformation values as the first vector coordinate data. The data processing module is configured to: Convert the first vector coordinate data into a first pixel matrix; Cut the signature into a plurality of geometric parts in a segmented preprocessing manner, and reassign pixel coordinates of each geometric part; Merge the pixel coordinates of each geometric part to obtain a pixel set, and only record different geometric serial numbers and coordinate values; The coordinate transformation values are used as part of an encrypted pixel matrix, wherein the coordinate transformation values include coordinate transformation values of the typical values and the atypical values; 6. The digital signature generation and authentication system of claim 5, wherein, The geometric serial numbers, coordinate values and coordinate transformation values are written into the encrypted pixel matrix, and redundant coordinate data in the first pixel matrix is deleted. The data processing module is configured to: Generate noise pixels and virtual coordinates thereof at a preset proportion of the pixel set; Use the noise pixels as confusion coordinate values of adjacent data of each geometric part; Generate a block image based on the confusion coordinate values, and obtain a position of the block image in a coordinate system of the first pixel matrix; Obtain noise pixel coordinates at a boundary of the block image; Obtaining updated coordinate positions of pixels in the block image after writing, and updating to the pixel set.

7. The digital signature generation and authentication system of claim 6, wherein, The data processing module is configured to: write the pixel data of the facial features as part of the obfuscated data after preprocessing, to the block image; generate a second key parameter based on the obfuscated data; perform a pixel migration operation on the first pixel matrix by combining the second key parameter with the first key parameter, to encrypt the first vector coordinate data.

8. The digital signature generation and authentication system of claim 7, wherein, The generation module is configured to: scan the facial features of the user to be authenticated, to obtain scanned facial feature data; compare the scanned facial feature data with the facial features in the second key parameter, to verify the validity and authenticity of the scanned facial feature data; when the verification is passed, decrypt the key data using the second key parameter; generate a digital copy based on the decryption result, and verify the authenticity of the digital copy by comparing it with the signature data in the second graphical interface; wherein the digital copy is a non-vector copy that has been decrypted and subjected to pixel migration.

9. The digital signature generation and authentication system of claim 8, wherein, The data processing module is configured to: record an offset value between a first position coordinate when the first terminal samples the facial features of the user, and a second position coordinate when the second terminal samples the facial features of the user; use the offset value as an additional key parameter, to participate in the encryption process of the first vector coordinate data together with the first key parameter and the second key parameter; store the additional key parameter in the key data in an encrypted form.

10. A digital signature generation and authentication method characterized by comprising: The method comprises the following steps: at a first terminal, generate a first graphical interface, and obtain first vector coordinate data of a signature of the user on the first graphical interface, in response to the signature performed by the user on the first graphical interface; at the first terminal, sample the facial features of the user; extract typical values and atypical values from the first vector coordinate data as first key parameters; extract feature points and non-feature points from the facial features as second key parameters; perform encryption of the first vector coordinate data by the first key parameters and the second key parameters, to obtain key data; transmit the key data to a second terminal; at the second terminal, verify the facial features of the user; decrypt the key data using the second key parameters; request the first terminal to generate a digital copy to a second graphical interface; wherein the digital copy is a non-vector copy that has been decrypted and subjected to pixel migration.

Images