6results about How to "Good attack performance" patented technology

The present invention belongs to the technical field of poisoning attack methods, and discloses a deep neural network poisoning attack method, constructs a double-layer superposition coupled multi-attention convolutional network, uses a clean target data set to pre-train the network, and then uses the pre-trained network to extract image feature maps, and generates corresponding weight vectors according to the number of key image features contained in the feature map, and then performs weighted fusion of these features to generate superposition coupled feature maps; constructs a perturbation screening network, expands the superposition coupled feature map and puts it into the perturbation screening network to obtain its confidence, and screens out the superposition coupled feature map with the highest confidence, and splices it with the clean image as a perturbation to generate a poisoned sample; selects a superposition coupled feature map with the highest confidence in each type of image as a perturbation and adds it to another type of image to generate a poisoned data set. The method of the present invention solves the problems of cumbersome poisoning sample generation process and high vulnerability in the existing poisoning attack method.

The application provides a trajectory embedding leakage prevention method and system, including the following: in a test environment, based on similarity calculation, multi-label classification, and recurrent neural network attack trajectory embedding to be attacked, any region in the space region that the original trajectory may pass through is obtained as the predicted privacy information of the original trajectory; a model improvement step: the trajectory embedding model is investigated, evaluated, and improved through the predicted privacy information of the original trajectory; a leakage prevention step: the improved trajectory embedding model is used to prevent trajectory embedding leakage. The application obtains the privacy information of the trajectory in the test environment, achieves good attack effect, overcomes the lack of attack technology in this aspect, and can prevent embedding trajectory leakage.

The invention discloses a distributed network routing attack generation method for a smart power grid, and belongs to the technical field of smart power grid system security. The method is characterized by comprising the following steps: step a, initializing parameters; b, updating an attacked sensor set in real time; c, obtaining an attack matrix; d, judging whether the attack matrixes of all the sensors are updated or not, and if the attack matrixes of all the sensors are updated, constructing a combined attack matrix of the system; e, tampering the measurement data of the intelligent power grid system according to the joint attack matrix phi k obtained in the step d; and f, judging whether the distributed network routing attack is ended or not. According to the distributed network routing attack generation method for the smart power grid, the problem that a novel network attack behavior in a smart power grid system is understood at present is solved, a system designer is assisted to complete a corresponding defense strategy, and safe and stable operation of the smart power grid is guaranteed.

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 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.