126 results about "Spoofing attack" patented technology

The invention relates to the technical field of face detection, and particularly discloses a face recognition system based on a face mask detection model, which is used for solving the problems of face recognition accuracy reduction and counterfeiting risk caused by mask shielding, counterfeiting attack and multi-source environment interference in high-security sensitive scenes such as a banking business window and the like. The system comprises a data acquisition and enhancement module, a feature extraction and multi-task neural network discrimination module, a counterfeit attack detection and risk blocking module, and a system deployment and model adaptive training module. According to the invention, through integration of multi-channel high-resolution visible light and infrared imaging, forgery attack sample enhancement based on the generative adversarial network, adaptive difficult sample sampling and multi-task deep discrimination network collaborative optimization, efficient recognition and real-time risk blocking of real and forgery mask faces are realized; and the security and robustness of a face recognition system in scenes such as banks are improved.

The invention discloses an MES (Manufacturing Execution System) login authentication method based on a face recognition technology, which relates to the technical field of industrial information security, and comprises the following steps of: constructing an authentication data acquiring a face image of an authorized user of an MES, extracting a reference face feature template after preprocessing, and constructing the authentication database; performing associated storage on the reference feature template, user identity information, preset operation authority and affiliated production station information to form an authentication database; according to the method, spoofing attacks are prevented through multi-mode living body detection, and the problem that a traditional password / key is easy to leak and borrow is solved in combination with uniqueness of human face biological characteristics; a person-post-terminal binding mechanism further limits permission abuse, and internal operation risks are reduced; the non-contact authentication does not need to memorize a password or carry a physical key, and is suitable for a working scene that a workshop operator wears gloves and holds tools; and the recognition passing rate in a complex industrial environment is improved through dynamic threshold optimization.

The invention discloses a multi-modal attack identification method fusing BMama and difference to guide trans-attention, which comprises the following steps: simulating a false data injection attack, a denial of service attack, an address resolution protocol spoofing attack and a domain name system spoofing attack, collecting physical layer sensor data and network layer flow data, and preprocessing multi-modal data; bMama is constructed to perform dynamic time modeling on multi-modal data, a graph neural network is combined to adversariate a variational auto-encoder, features of a power grid system topology and a communication topology structure are fused, and robustness of potential representation is enhanced through adversarial training; the method comprises the following steps of: guiding feature complementary fusion by using modal difference through a difference guide iteration cross-attention fusion mechanism, improving the capability of distinguishing complex attacks, finally carrying out attack detection and classification on fused modals, and executing end-to-end optimization according to a weighted combination of loss of each part. The method can effectively detect and classify the multi-modal attack in the smart power grid, and enhances the safety and reliability of a complex system.

The invention discloses a self-adaptive finite time fuzzy safety control method for a flexible joint mechanical arm, which comprises the following steps that a flexible joint mechanical arm state space model influenced by spoofing attack is established, and a control signal comprises an unknown time-varying parameter and an unknown bounded attack function; introducing a Nussbaum function meeting a preset limit integral property; designing a control method based on a finite time stability principle, and ensuring that a system state converges to a bounded residual set within finite time; a fuzzy logic system is adopted to approach an unknown nonlinear function in the mechanical arm model; defining an error variable through coordinate transformation, and constructing a parameter which exponentially decays along with time; constructing a Lyapunov function containing the exponential decay parameter, and designing a virtual control function, a controller and a parameter adaptive law based on the function; and the Nussbaum function is constructed to be used for processing the unknown time-varying parameters. According to the invention, the influence of spoofing attacks on state signals can be reduced.

The invention relates to the technical field of household equipment intrusion detection, in particular to a mimicry intrusion detection method and system for household equipment, and the method comprises the steps: S0, starting credible verification and initialization; the method comprises the following steps: S1, carrying out multi-modal feature fusion processing; s2, disturbance type joint detection; s3, graded elastic response is carried out; s4, updating the self-adaptive model; s5, identifying a semantic exception instruction; and S6, neural morphology calculation is accelerated. According to the method, damage attack path dependence is detected through dynamic disturbance, multi-modal features are fused through a modal alignment mechanism, low-power-consumption acceleration is achieved through neuromorphic hardware, semantic anomaly instruction recognition and brain-like feedback offline optimization are combined, and the core problem that high-precision detection and high robustness cannot be considered at the same time in the prior art is solved; and particularly, real-time attacks and semantic spoofing attacks of unknown vulnerabilities are effectively resisted.

The invention provides a pinned pulse safety synchronization control method and system of a multi-coupling time-delay network, and the method comprises the technical schemes: building a coupling time-delay dynamic network model, constructing a mathematical description of a random spoofing attack, designing a pinned pulse safety controller, and deducing a Lyapunov stability discriminant. Through defining an error system of a following network and a target network, under a pinned pulse safety control framework, based on a pulse system theory, system stability is analyzed, an attack probability is described in combination with a Bernoulli random variable, a pinned pulse control node selection strategy is finally designed, and safety synchronous control is successfully realized. The mechanism can effectively extract time delay information with a stabilization effect in a continuous system, and fuses the time delay information into the design of an anti-attack containment pulse safety controller, so that the synchronization safety of the system is remarkably improved, the resource allocation efficiency is optimized, and the attack influence is weakened by utilizing inherent time delay.

The present invention improves determination accuracy of a spoofing attack on biometric authentication.　An information processing device (10) determines the brightness of image data (13) from a plurality of pixel values included in the image data (13). The information processing device (10) generates, from the image data (13), frequency component data (14) indicating a frequency component of a frequency section corresponding to the brightness so as to indicate a frequency component of a frequency section (16a) when the brightness is at a level (15a), and to indicate a frequency component of a frequency section (16b) including the frequency higher than that of the frequency section (16a) when the brightness is at a level (15b) that is higher than the level (15a). The information processing device (10) inputs the image data (13) and the frequency component data (14) into a machine learning model (17), thereby determining whether the image data (13) indicates a spoofing attack on biometric authentication.

The invention relates to the technical field of Internet of Vehicles information security, and discloses an Internet of Vehicles-oriented Beidou signal spoofing detection and mitigation intelligent system and method, and the system comprises a multi-dimensional data sensing and preprocessing module, a deep learning joint detection module, and a security mitigation and reputation management module. The method comprises the following steps: firstly, extracting a physical layer signal feature and a network flow stability feature and generating a multi-dimensional feature vector; secondly, performing feature compression and preliminary screening by using an auto-encoder, analyzing a time sequence evolution rule through a long-short-term memory network, and outputting a judgment probability; and finally, executing hierarchical defense according to the judgment probability, responding to local threats by dynamically adjusting a measurement noise covariance matrix or a hard isolation strategy, evaluating network node reputation based on a path damage index, and adding abnormal nodes into a dynamic blacklist. Through the multi-dimensional feature fusion and deep learning cascade architecture, the spoofing attack detection accuracy is improved, and the diffusion of false information in the Internet of Vehicles is effectively blocked.

The application provides a multi-agent system mean square consensus control method under hybrid attack, relates to the technical field of intelligent control, and comprises the following steps: establishing a multi-agent system model, designing a controller, on the basis, constructing an error system between a follower agent and a leader, and establishing a mean square consensus condition of the multi-agent system under a deception attack and a DOS attack, so that the multi-agent system is controlled to realize leader-following mean square consensus. The application improves the control strategy by comprehensively considering the possible deception attack and DOS attack during the working period of the multi-agent system, so that the leader-follower mean square bounded consensus is realized, and the control efficiency and control precision are improved.

The invention discloses a safety control method of a high-order chain type multi-agent system under spoofing attack, and belongs to the technical field of safety control of multi-agent systems. The method comprises the following steps: establishing a dynamic model of a high-order chain type multi-agent system; constructing an extreme attack scene in which all communication links are subjected to bounded spoofing attacks; based on a backstepping control method, a distributed fixed time security control protocol is designed for a system, and the protocol counteracts attack influence by designing a virtual control strategy and a Lyapunov function; a Lyapunov stability theory is utilized to prove that under the action of the protocol, a system tracking error can be converged to zero within fixed time, so that safe and consistent tracking is realized. The defect that the prior art mainly aims at a linear system or only can realize asymptotic convergence is overcome, the method is particularly suitable for scenes such as non-complete constraint wheeled mobile robots, and the robustness and the rapid recovery capability of the system under extreme spoofing attacks are effectively improved.

The invention relates to the technical field of array antenna signal integrity detection, and discloses an array antenna signal integrity deception detection method and system, and the method comprises the steps: obtaining a receiving signal in an array antenna, and analyzing the quality parameter of the receiving signal; according to the quality parameter, identifying a receiving unit with inherent signal bias in the array antenna, and marking the receiving unit with inherent signal bias as a special processing unit; for a special processing unit, establishing and continuously updating a defect feature model representing inherent signal bias of the special processing unit under the condition of no deception signal; inherent signal bias is eliminated from the real-time received signals of the special processing unit based on a defect feature model, and signals after bias elimination are obtained; detecting whether an abnormal phase or frequency drift exists in the signal after the offset is eliminated; and when the detected abnormal phase or frequency drift exceeds a preset spoofing judgment threshold, determining that a spoofing attack exists. The problem that spoofing attacks are difficult to recognize is effectively solved.

To provide a positioning device that can reduce the risk of decreased positioning accuracy in an environment of spoofing attacks. [Solution] A positioning device comprising: a receiving unit that receives a first satellite signal in a first frequency band and a second satellite signal in a second frequency band different from the first frequency band transmitted from a first satellite; a positioning unit; a determination unit that compares the value of a predetermined parameter included in the first satellite information of the first satellite based on the first satellite signal with the value of the predetermined parameter included in the second satellite information of the first satellite based on the second satellite signal to determine whether or not the first satellite is spoofed; and a control unit that controls the positioning unit so as not to perform positioning using the first satellite information and the second satellite information of the first satellite when the determination unit determines that the first satellite is spoofed.

A method for detecting anomalies in image data captured by a vehicle sensor includes receiving first and second image frames, and first and second observation clouds generated based on LiDAR data capt

The invention provides a voice anti-cheating method and system based on double interactive query, and relates to the technical field of voice recognition. The invention provides an audio understanding model based on double interactive query, aiming at the technical problem that the performance and the efficiency of deep counterfeit voice detection cannot be well considered in the prior art. According to the model, a local mode branch in a double-branch processing module based on cross attention is used for extracting local acoustic artifacts in forged voice, a global context branch is used for capturing global context anomalies, and meanwhile, cross attention mechanisms in the global context branch and the local mode branch are symmetrical layer by layer by using a symmetric collaborative interaction mechanism, so that the local acoustic artifacts in the forged voice are extracted. The two heterogeneous branches are subjected to deep interactive fusion, and global and local representations can be mutually complemented and jointly optimized in the whole network, so that more comprehensive feature representation for forged voice is formed, and the detection precision for known and unknown spoofing attacks is improved while the complexity of the model is remarkably reduced.

A system and method for identifying compromised systems, even where cyber security measures are in place, continuously monitors system parameters against a set of predefined thresholds. If the system violates those thresholds, either instantaneously or over a period of time, the system determines that unknown processes are using the system; those processes may be unauthorized processes loaded via a successful spoof attack. The system may monitor CPU usage, power usage, temperature, memory access, data storage access, data transmission rates, etc. The system may execute some remedial action when unauthorized processes are suspected.

This invention focuses on an additional error cause and an attack probability metric for UE to report spoofing attack to server. While the detection algorithm on UE and the decision algorithm on server can be open for implementations, this contribution proposes to leverage server-UE authentication mechanism and calculate the attack probability metric by the number of authentication errors within a time window.

The application relates to an adaptive filtering method based on sliding window innovation evaluation and joint constraint. The method comprises the following steps: calculating the innovation covariance through parallel calculation theory and the empirical innovation covariance estimated based on the sliding window, dynamically quantifying the mismatch degree of the two, and adaptively amplifying the GNSS measurement noise covariance according to the mismatch degree, so as to suppress the weight of abnormal signals in fusion. The second module is a state prediction covariance joint constraint unit, which prevents excessive convergence of filtering by introducing a dynamic forgetting factor and applying a minimum boundary constraint related to the position state to the prediction covariance matrix, thereby ensuring that the LiDAR maintains effective state correction capability within the continuous GNSS update interval. Through the synergistic effect of the above mechanisms, the method realizes early perception and active inhibition of advanced spoofing attacks, and significantly improves the positioning safety and robustness of the multi-sensor fusion system in a complex dynamic environment.

The invention discloses a clustering consistency control method, system and equipment for multi-agent system safety. The method comprises the following steps: constructing a multi-agent system clustering network and a dynamic model based on external disturbance factors; obtaining communication topology between the intelligent agents based on the clustering network; the method comprises the following steps of: constructing an adaptive event triggering strategy with a memory characteristic on a clustering network, converting a system clustering consistency problem into a convergence analysis problem of an error system, then obtaining sufficient conditions for a distributed controller to meet anti-interference performance and mean square index stability through a Lyapunov-Krasovskii functional, and finally decoupling nonlinear factors to obtain an LMI condition; and solving controller gain and specified related parameters to realize security clustering consistency control of the multi-agent system in a communication resource limited and spoofing attack environment. According to the method, the consistent achievement of multi-agent system clustering and safe and stable operation under spoofing attack and disturbance network communication can be ensured.

The application discloses a method for adaptive secure consensus control of a multi-agent spatio-temporal dynamic system with unknown boundary nonlinearity under hybrid attacks, comprising the following steps: constructing a multi-agent spatio-temporal dynamic system model with unknown boundary nonlinearity and a virtual leader model; establishing a hybrid network attack model containing deception attacks and denial of service (Dos) attacks, and using an adaptive radial basis neural network to approximate the unknown boundary nonlinearity function; defining a consensus error signal to obtain a consensus state error system; designing a composite adaptive neural network secure boundary consensus control scheme, constructing a Lyapunov function for the error system, and obtaining a sufficient condition for the error system to realize mean square secure consensus control. The application effectively solves the problem that the traditional method is difficult to simultaneously cope with complex network attacks and unknown boundary nonlinear disturbances, and significantly improves the security and robustness of the system.

In an embodiment of the present application, a wireless communication method, a station (STA), and an access point (AP) are provided. If a service set identifier (SSID) in a first frame transmitted by an AP is an SSID that the STA has previously connected to, the STA determines whether the AP is spoofed by another device based on identity information. This can solve the risk of user privacy leakage caused by a "spoofed AP" attack, and is easy to implement because it increases signaling overhead relatively little and has minimal impact on system throughput. The wireless communication method includes the following steps: a station receives a first frame. The first frame includes identity information, which is determined based on first secret information and time information of the access point. If the SSID in the first frame is an SSID that the station has previously connected to, the station determines whether the access point is spoofed by another device based on the station's time information, the first secret information, and the identity information.

The invention discloses a preemption and perception cross spoofing attack detection method based on systematic residual check. The method comprises the following steps: acquiring a damaged signal subjected to a PSCS attack; performing discrete Fourier transform on the damaged signal to obtain a plurality of resource elements, and extracting a phase gradient and an amplitude deviation for each resource element; defining a non-attack state constraint function and an attack state constraint function by using the phase gradient and the amplitude deviation corresponding to each resource element, so as to express the construction of test statistics as a minimum and maximum optimization problem; a minimum and maximum optimization problem is converted into a semi-definite programming problem through a kernel tensor completion technology, and test statistics are obtained by solving the semi-definite programming problem; based on the test statistics, calculating a detection threshold according to a false alarm probability; and calculating the current test statistic of the to-be-detected signal in the current time slot, and if the current test statistic is greater than the detection threshold, judging that the PSCS attack exists, thereby realizing the effective seizing and sensing cross spoofing attack detection method.

The application relates to the technical field of fraud detection, and discloses a detection method and system for spoofing attacks / natural electromagnetic interference, which comprises: a first detection quantity based on absolute tracking loop output (ATLO); mobile variance filtering processing (ATLO-MV) is performed on the first detection quantity to construct a second detection quantity; and the detection probability information of the second detection quantity of ATLO-MV of multiple satellites is used to distinguish spoofing attacks, natural electromagnetic interference and no interference. Through construction of the first detection quantity based on absolute tracking loop output, subtle fluctuations in tracking loop output can be accurately captured; the second detection quantity of ATLO-MV obtained through mobile variance enhancement processing effectively improves detection sensitivity and anti-noise performance; finally, a new type of detection algorithm is constructed through multi-satellite joint processing (ATLO-MV-MSC) of ATLO-MV, the distinction between no interference, natural electromagnetic interference and spoofing attacks is realized, and the pain point of fuzzy judgment existing in traditional algorithms is solved.

The application discloses a kind of industrial information physical system's deception attack detection method, comprising the following steps: step 1: the information physical system model with different security level data transmission channel is established, discrete linear time-invariant state space model is established, and the deception attack process description under this model is established;Step 2: the sparse sampling security data transmission channel is established, and the data in unreliable channel is encrypted;Step 3: residual error is constructed based on the data correlation between different channels;Step 4: the residual error change caused by deception attack is quantified, and the optimal weight matrix is established to improve the detection performance;Step 5: set detection strategy and detection threshold, calculate detection statistics, and complete deception attack detection.The application realizes deception attack detection by quantifying the change of data correlation caused by attack, and can effectively solve the problems of certain limitations of existing deception attack detection methods and application in multi-channel information physical system.

The invention discloses a multi-source undisturbed attack detection and safe dynamic positioning method for switching an unmanned ship system, and the method comprises the steps: building an unmanned ship quality switching model through a hysteresis quantizer, inhibiting residual buffeting through an event triggering protocol, and transmitting a state and quality mode switching signal to a shore base; designing a multi-source undisturbed rate residual calculation model based on the state observer, and eliminating the influence of quality switching and event triggering on the residual; constructing a spoofing attack detection function, obtaining a state and modal detection result, and designing a safety controller according to the state and modal detection result; meanwhile, an event triggering and watermarking mechanism is introduced into a controller-actuator channel to resist spoofing attacks; according to the method, a closed-loop system is constructed based on a double-event triggering protocol, finally, safe dynamic positioning of the quality switching unmanned ship is achieved, detection false alarm and missing alarm caused by rate residual buffeting due to switching behaviors and data updating during triggering can be overcome, and the detection strategy is achieved to give an alarm only when a spoofing attack occurs.

Biometrics are increasingly used to provide authentication and / or verification of a user in many security and financial applications for example. However, “spoof attacks” through presentation of biometric artefacts that are “false” allow attackers to fool these biometric verification systems. Accordingly, it would be beneficial to further differentiate the acquired biometric characteristics into feature spaces relating to live and non-living biometrics to prevent non-living biometric credentials triggering biometric verification. The inventors have established a variety of “liveness” detection methodologies which can block either low complexity spoofs or more advanced spoofs. Such techniques may provide for monitoring of responses to challenges discretely or in combination with additional aspects such as the timing of user's responses, depth detection within acquired images, comparison of other images from other cameras with database data etc.

Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for visual authentication. In some implementations, a method may include obtaining images of a person at a property; detecting a discontinuity in an appearance of the person in the images of the person at the property; determining that the discontinuity does not correspond to a known occlusion; and providing an indication of a potential spoofing attack.

This application discloses a security control method and system for smart cockpits. The solution acquires user authentication information, historical behavior baselines, and authentication features. It continuously collects current environmental and user behavior information, dynamically determines user trust levels based on the aforementioned information, and adjusts user operation permissions in real time according to the trust level. Upon detecting a user interaction command, it acquires multimodal signals within the corresponding time window of the command and performs multi-dimensional consistency verification on the command based on authentication features. Based on the verification results and the user's current operation permissions, it determines the command execution strategy. This application's technical solution achieves precise matching of permissions and real-time risks through dynamic trust level assessment. Relying on multimodal signal verification, it accurately identifies abnormal interactions and deception attacks, achieving refined security control of interaction commands. Through the coordinated decision-making of trust level, operation permissions, and interaction verification results, it improves the reliability and adaptability of smart cockpit security control.

The application discloses a GNSS spoofing detection method based on adaptive RAIM and hidden space diffusion model, and relates to the fields of satellite navigation and artificial intelligence.The method comprises the following steps: constructing an adaptive pseudo-range residual feature extractor, wherein the adaptive pseudo-range residual feature extractor is composed of a weight adaptive network and a weighted least squares RAIM; the weight adaptive network is constructed by a graph convolutional neural network, can adaptively correct the pseudo-range observation weight matrix of the weighted least squares RAIM, and can enhance the sensitivity of the pseudo-range residual to the geometric consistency destruction caused by spoofing; the weighted least squares RAIM processes the pseudo-range residual on the basis to extract the multi-scale trend features; constructing a hidden space diffusion model, wherein the hidden space diffusion model is trained by using the multi-scale trend features which are not spoofed, and performs spoofing detection through a state evaluation function.The application can effectively improve the detection performance of the receiver on the GNSS spoofing attack.

The invention belongs to the technical field of chemical industry safety automatic control, and particularly relates to a control method of a two-stage chemical reactor system under spoofing attack and unknown disturbance. Comprising the following steps: establishing a state equation and a general second-order system state space expression according to operation state information of a two-stage chemical reactor system; in consideration of spoofing attack, constructing a specified performance function and error signals, introducing a first-order filter, and converting a first error signal into a specified performance error signal; according to the constructed error signals, respectively constructing a Lyapunov function for the two-stage system, and designing a corresponding virtual controller, an adaptive law and a disturbance observer under a backstepping method framework; and a dynamic event triggering mechanism is combined to reduce data transmission quantity and reduce attack risks. According to the method, the stability, the safety and the operation efficiency of the two-stage chemical reactor system in a complex environment can be effectively improved, deception attack and disturbance are reliably inhibited, and efficient and safe operation of the reaction process is guaranteed.