22results about How to "Increase aggressiveness" patented technology

The invention discloses an anti-quantum-attack national secret IPSec communication system and method, and belongs to the technical field of information security. The national secret IPSec communication system capable of resisting the quantum attack in the scheme comprises a traditional IPSec device, an anti-quantum IPSec device agent and a mixed IPSec device. Traditional IPSec equipment does not support an anti-quantum cryptography algorithm, and hybrid IPSec equipment has a traditional cryptography technology and an anti-quantum cryptography technology at the same time. And the anti-quantum IPSec equipment proxy performs anti-quantum cryptography algorithm transformation on a message sent by the traditional IPSec equipment and then sends the message to the mixed IPSec equipment, and performs anti-quantum cryptography algorithm inverse transformation on a message sent by the mixed IPSec equipment and then sends the message to the traditional IPSec equipment. According to the scheme, the quantum attack resistance of the system is improved in a manner of incrementally deploying the anti-quantum IPSec equipment agent on the IPSec equipment, the transformation period is short, and the transformation cost is low.

The invention relates to the technical field of adversarial learning, in particular to an adversarial sample generation device and method based on space-frequency fusion, and the method comprises the steps: collecting image data, and building a training data set for adversarial sample generation, including building a target class image training set and a to-be-generated disturbance image training set; performing spatial domain block data enhancement and frequency domain data enhancement on an image in the to-be-generated disturbance image training set to obtain a data enhanced image; processing the data enhancement image by adopting a generator to obtain a disturbance image; based on the images in the target class image training set, a discriminator is adopted to carry out space domain discrimination and frequency domain discrimination on the disturbance images, and space-frequency domain loss is obtained; taking minimization of the space-frequency domain loss as an optimization requirement, and updating network parameters of the generator; obtaining a trained generator until the space-frequency domain loss is smaller than a preset value, and generating an adversarial sample by adopting the trained generator; according to the method, the adversarial sample with better mobility can be generated.

The invention discloses an adversarial sample generation method and device for a face forgery detection model. The method comprises the following steps: obtaining a real category attention graph and a false category attention graph of an original sample by using a white-box face counterfeiting detection model, fusing the real category attention graph and the false category attention graph to obtain a fused attention graph, and processing the fused attention graph to obtain a dual hard mask; generating global disturbance of the original sample by using a spatial domain disturbance generator obtained by pre-training; cutting the global disturbance by using the dual hard mask to obtain local disturbance; and superposing the local disturbance to the original sample to obtain an adversarial sample. According to the scheme, the face forgery detection model can be attacked from a real area and a false area, a high attack success rate is achieved for the white box face forgery detection model and the black box face forgery detection model, and the attack effect of the confrontation sample is improved.

The invention provides a physical confrontation coating generation method and device for a vehicle target detector. The method comprises the following steps: acquiring a mask image, a vehicle image and shooting camera visual angle data from a multi-weather vehicle data set; segmenting the vehicle image by using the mask image to obtain a foreground vehicle image and a background image of the vehicle image; inputting the foreground vehicle image, predetermined vehicle model data, a vehicle UV image and shooting camera visual angle data into an autonomously designed differentiable end-to-end advanced neural renderer to render the vehicle image in a specific scene and visual angle; combining the rendered vehicle image with the background image to form a complete image, inputting the complete image into a random disturbance module to add disturbance, and inputting the disturbed image into a target detector to obtain a detection result; the detection result is used, loss is calculated through a self-designed loss function, and vehicle coating is optimized through gradient back propagation. The vehicle confrontation coating generated by the method can realize accurate deployment and has better robustness.

The invention discloses a deceptive texture-based black box adversarial sample generation method, which comprises the following steps of: acquiring a plurality of initial optimization variables, the initial optimization variables being an array of 2 + m * m dimensions, the first two-dimensional numerical values being used for representing coordinates of an adversarial patch center in an image, the last m * m-dimensional numerical values being used for representing a pixel value of an adversarial patch, and the pixel value being 1 or 0; decoding the last m * m-dimensional numerical value of the initial optimization variable to obtain a corresponding adversarial patch, and pasting the adversarial patch in the image according to the first two-dimensional numerical value of the initial optimization variable to obtain an adversarial sample; and inputting the adversarial samples corresponding to the plurality of initial optimization variables into the deep neural network model to obtain a detection result output by the model, and performing optimization variable iterative updating based on the plurality of initial optimization variables and the detection result to obtain a final optimization variable and a corresponding adversarial sample thereof. The method can improve the cheating of the anti-patch, improves the attack effect of the anti-sample, improves the optimization efficiency, and reduces the optimization cost.

The invention relates to the field of artificial intelligence confrontation technology and the like, and discloses a data-free black box confrontation sample generation method based on attention enhancement, which comprises the following steps: randomly sampling a noise space, and generating synthetic data # imgabs0 # by an input generator; querying decision output of a black box target model # imgabs2 by using the synthetic data # imgabs1 #, and caching an input-output pair; enhancing the substitution model by using an attention enhancement module, and training the enhanced substitution model; training a generator by using a joint structure information learning strategy; the cached input and output pairs are replayed, and the enhanced substitution model is further trained; constructing an adversarial sample on the enhanced substitution model by applying a white-box attack strategy, and migrating to a black-box target model to implement attack; the problems that an existing substitution model is low in learning efficiency for different synthetic data, the synthetic data generated by the generator is poor in diversity, and the substitution model is low in training efficiency are solved, and by optimizing the substitution model and the generator learning strategy, the optimized substitution model accurately simulates black box target model decision output.

The invention relates to the technical field of prediction and evaluation of lung cancer samples, and discloses a prediction and evaluation method of a lung cancer sample, which comprises the following steps: collecting clinical information of a lung cancer patient, acquiring biological data of the lung cancer sample, sorting medical image data, extracting key genes, proteins or pathway characteristics from the biological data, important features related to the lung cancer are screened by using a statistical method or a machine learning algorithm, a proper machine learning or deep learning model is selected according to data characteristics and a prediction target, and the interpretability, stability and calculation complexity of the model are considered. According to the method, tumors with high-risk characteristics, such as tumors with high invasiveness and high metastasis potential, can be found and intervened in time through prediction and evaluation of lung cancer samples, so that the disease progress is delayed, the treatment effect is improved, the treatment effect and disease change can be monitored through regular prediction and evaluation of the lung cancer samples in the treatment process, and the treatment effect is improved. The treatment scheme is adjusted in time, and the maximization of the treatment effect is ensured.

The utility model belongs to the technical field of drilling tools, and particularly relates to a self-driven rotating tooth and a drill bit. The self-driven rotating tooth comprises a rotating sleeve; the core tooth is coaxially and rotatably arranged on the rotating sleeve, a driving combination surface is arranged on the working surface of the core tooth, and the driving combination surface is configured to enable the core tooth to rotate relative to the rotating sleeve when being subjected to axial force. The working face of the core tooth is provided with the driving combination face, so that the core tooth is constructed into the special-shaped tooth, on one hand, the core tooth can automatically rotate in the drilling process without a side corner, can be installed at the position of a cutting tooth of a conventional PDC drill bit for use, and can be exchanged with the conventional PDC cutting tooth for use; and large-area popularization and application of the rotating tooth are facilitated, and the impact resistance and aggressiveness of the core tooth can be improved. On the other hand, the impact resistance and aggressiveness of the core tooth can be improved.

The invention discloses a cross-camera physical countermeasure attack method and system for pedestrian detection, and relates to the field of artificial intelligence security. The method comprises the following steps: forming a data pair from an original image, a target image obtained by processing the original image through a camera ISP, and randomized parameters obtained by randomizing key parameters; constructing a camera ISP proxy network, and training the camera ISP proxy network according to the data pair to form a camera ISP proxy network model; processing an adversarial patch to be optimized through the camera ISP proxy network model to obtain an ISP processing adversarial patch and applying the ISP processing adversarial patch to a pedestrian data set; and constructing an adversarial optimization framework according to the target detector and the camera ISP proxy network model, and generating a cross-camera adversarial patch in the adversarial optimization framework. The cross-camera adversarial patch obtained by the invention can continuously and effectively attack a target on different pedestrian detection devices, and the success rate of physical adversarial attacks is improved.

The invention provides a bispecific antibody capable of binding to PD-L1 and VEGF (vascular endothelial growth factor). The bispecific antibody comprises a first binding domain capable of binding to PD-L1 and a second binding domain capable of binding to VEGF. The bispecific antibody provided by the invention is combined with PD-L1, so that the immunosuppression of tumor cells on T cells can be relieved, and the anti-tumor function of an immune system can be recovered; meanwhile, by combining the bispecific antibody with VEGF, the growth of the tumor can be slowed down, the blood supply of the tumor can be reduced, and even the tumor blood vessel can be normalized, so that the immune environment is improved, and the attack ability of immune cells on the tumor is enhanced.

This invention provides an artificial intelligence (AI) model security detection system based on adversarial example injection, relating to the field of AI security. The system includes the following modules: an adversarial example generation module for dynamically generating adversarial examples for the AI ​​model; a multi-level injection module for controlling the injection of adversarial examples at each level of the AI ​​model; an adversarial example fusion module for intelligently coordinating the generation and fusion of adversarial examples with physical constraints and those with digital perturbations; a multi-dimensional monitoring module for real-time monitoring of the AI ​​model's output, internal features, and resource consumption; a security assessment module based on a deep metric learning algorithm to output assessment results; and a defense suggestion module to generate defense schemes based on the assessment results. This invention improves the efficiency of AI model security detection and provides reliable technical support for the secure deployment and continuous optimization of AI models.

The application relates to a conical complex piece and a drill bit, which comprises a base and a conical tooth arranged on the top surface of the base, the bottom end of the conical tooth is connected with the top surface of the base, the top end of the conical tooth is provided with an impact surface for contacting with the external environment, first recessed surfaces and second recessed surfaces are arranged on the circumferential outer wall of the conical tooth and are spaced apart in the circumferential direction, and the side edges of the first recessed surfaces and the second recessed surfaces which are close to each other both extend along the generatrix direction of the conical tooth, and a ridge is formed between the first recessed surfaces and the second recessed surfaces. The ridge can effectively scrape the stratum structure during rotation, improves the attackability and the ability of eating into the stratum, and finally improves the efficiency of the conical complex piece during drilling. In addition, the impact surface arranged at the top end of the conical complex piece has strong impact resistance when contacting with the stratum, and finally the drill bit has strong impact resistance and strong scraping effect.

This invention relates to fields such as AI adversarial techniques, and discloses a data-free black-box adversarial example generation method based on attention enhancement, comprising: randomly sampling a noise space, inputting it into a generator to generate synthetic data. ; Utilizing synthetic data Query black-box target model The system calculates the decision output and caches the input-output pairs; it strengthens the alternative model using an attention enhancement module and trains the enhanced alternative model; it trains the generator using a joint structural information learning strategy; it replays the cached input-output pairs to further train the enhanced alternative model; it employs a white-box attack strategy to construct adversarial examples on the enhanced alternative model and transfers them to the black-box target model to carry out the attack; it overcomes the problems of low learning efficiency of existing alternative models for different synthetic data, poor diversity of synthetic data generated by the generator, and low training efficiency of alternative models, and by optimizing the learning strategies of the alternative model and the generator, the optimized alternative model can accurately simulate the decision output of the black-box target model.

The invention discloses a self-assembly preparation method and application of multi-enzyme active nano-zinc oxide for treating salmonella enteritis, a trace amount of oleylamine is added as a protective agent, a self-assembly nano-enzyme is synthesized by a simple method, and the direct antibacterial effect of ZnO is improved; the minimal inhibitory concentration of ZnO synthesized by the same method in vitro is 250 [mu] g / mL, the minimal inhibitory concentration of ZnO doped with trace Cu and Mn is about 30 [mu] g / mL, and the bacteriostatic efficiency is improved by about 8 times; trace elements of copper (Cu) and manganese (Mn) are doped into a ZnO nano material, so that the ZnO nano material is endowed with various enzyme activities, peroxidase activity is exerted under the acidic condition of the stomach to generate bactericidal active oxygen, and superoxide dismutase and catalase activity for resisting oxidative stress are exerted when the ZnO nano material reaches neutral intestinal tracts, so that inflammation of the intestinal tracts is relieved; the traditional Chinese medicine composition can play a role in the acidic state of the stomach, can relieve inflammation of the intestinal tract in the intestinal tract, and can completely adapt to the environment of the gastrointestinal tract.

This invention discloses a multi-objective evolutionary modeling method for fake data attacks in power system CPS (Computer-Powered Systems), belonging to the field of data attack technology. It solves the problem of insufficient attack flexibility in existing technologies, which fails to provide a foundation for power system defense. This invention models attacks through a three-step attack-defense game: attack gene generation, optimization, and evolution. In the gene generation stage, gene encoding technology is used to construct attack gene units from the decoupled attack offset and tag policy matrix, and these units are then assembled into base pair structures by aligning and splicing them. In the gene optimization stage, a multi-objective fitness function is constructed based on concealment and attack effectiveness objectives. Using residuals and attack effectiveness as objectives, a multi-objective collaborative screening between destructiveness and concealment is achieved to obtain optimized genes. In the gene evolution stage, multi-point crossover and single-point crossover operations are used for the attack chain and concealment chain of the optimized genes, respectively, to enhance the attack effectiveness.

The invention discloses a vertical federated learning-oriented hidden backdoor attack method, device and product, and the method comprises the steps: analyzing two attack modes of an input space and a potential space, and researching the risk that an attacker embeds a backdoor into a vertical federated learning model under the condition that global data or labels are not directly intervened; the input space attack is characterized in that in a vertical federation learning model training process, part of input samples are replaced and a trigger is injected, so that a top-layer model learns association between a backdoor trigger and a target label, and the top-layer model is guided to carry out error classification on the samples with the trigger in a reasoning stage; according to the potential space attack, an attacker directly acts on a feature embedding space of a local model of the attacker in the training process of the vertical federated learning model, and an embedding vector is adjusted by utilizing an optimization strategy so as to generate a specific backdoor response in a top layer model. According to the method, a solid foundation is laid for design and optimization of a defense mechanism, and security improvement of the VFL technology is promoted.

This application discloses an image processing method, apparatus, device, and storage medium, belonging to the field of artificial intelligence technology. The method includes: acquiring an original image; performing feature encoding processing on the original image to obtain a first feature map; acquiring a second feature map and a third feature map of the original image based on the first feature map; wherein the second feature map represents an image perturbation to be superimposed on the original image, and each position on the third feature map has different feature values, each feature value being used to characterize the importance of the image feature at the corresponding position; generating a noisy image based on the second and third feature maps; and superimposing the original image and the noisy image to obtain a first adversarial example. This application can generate high-quality adversarial examples, thereby achieving good attack effects.

This invention provides a robust adversarial camouflage generation method, system, and storage medium for monocular depth estimation in multi-view and complex environments. The method includes: Step S1, scene data acquisition: acquiring forward image data during vehicle movement; Step S2, adversarial texture rendering; Step S3, multi-view image acquisition: randomly selecting different angles, distances, and bias parameters, obtaining the corresponding camera positions through a transformation function, and using a differentiable renderer to obtain multiple object images with different angles, distances, and offsets, along with corresponding masks; Step S4, complex physical domain environment enhancement; Step S5, adversarial loss: constructing an adversarial loss function; Step S6, multi-view joint optimization. The beneficial effects of this invention are: overcoming the limitations of existing methods for object detection models and their difficulty in directly transferring to regression tasks, achieving robust multi-view adversarial attacks against texture-sensitive models like MDEs in complex physical domains.

The present invention discloses a deep reinforcement learning agent selection attack method based on trajectory approximation. t by K The attack trajectory formed by all attacks in the first step is the best trajectory. K The attack trajectory formed by no attack is the worst trajectory. By approaching the best trajectory while avoiding the worst trajectory, N The attack strategy with the best attack perturbation distribution is selected from the random attack strategies for subsequent K The present invention achieves the approximation of the attack trajectory of the entire round in the reinforcement learning environment through the attack trajectory planning of each step, maximizes the probability of the attack trajectory with the minimum cumulative reward, and effectively improves the attack effect at a lower attack frequency while maintaining the attack effect at a higher attack frequency.

This invention discloses an active face image protection method, system, and storage medium, relating to the field of network information security technology. The method includes: acquiring the original face image to be protected; generating an adversarial perturbation intended to be superimposed onto the original face image; iteratively optimizing the adversarial perturbation based on preset optimization objectives and constraints; wherein the optimization objective is configured to calculate and maximize the geometric position difference of facial key points between the original face image and the image after superimposing the adversarial perturbation, thereby disrupting the facial geometric structure features in the protected image; the constraints include joint spatial and frequency domain constraints, using a frequency domain mask to apply differentiated constraints to the coefficient values ​​of the adversarial perturbation in the frequency domain, and limiting the maximum amplitude of each pixel in the spatial domain; finally, superimposing the adversarial perturbation that meets the conditions onto the original face image to obtain the face protection image. This invention can effectively defend against malicious semantic editing of generative models while maintaining the visual quality of the image.

This invention discloses a backdoor attack method for deep neural network models, comprising: constructing and pre-training a spatial adaptive feature selection network; processing images by dividing them into blocks and inputting them into the pre-trained spatial adaptive feature selection network, and introducing a weighted ranking mechanism to generate trigger materials; constructing a feature labeling network, inputting labels into the feature labeling network to generate a label mapping map; and generating poisoned samples using the trigger materials and the label mapping map. This invention's deep neural network model backdoor attack method solves the problem of low attack success rate caused by the simple trigger structure and weak spatial adaptability in existing technologies.

This invention belongs to the field of image processing and discloses a method and related apparatus for generating adversarial images for deepfake detection models. The method includes acquiring an original image and inputting it into a preset adversarial artificial degradation model to obtain an initial adversarial image; inputting the initial adversarial image into a preset image restoration model to obtain an adversarial image; wherein the adversarial artificial degradation model is obtained by: acquiring an image dataset containing the initial image and a degradation image based on the initial image; constructing the initial artificial degradation model and training it using the image dataset to obtain an artificial degradation model; and training the adversarial nature of the artificial degradation model using the image dataset based on a joint loss to obtain the adversarial artificial degradation model. This method helps to transform the distribution of adversarial images into the distribution of real images, avoids significant noise patterns, possesses high visual quality and fidelity, provides guidance for optimizing deepfake detection models, and thus improves the quality of deepfake image detection.