15results about How to "Improve attack ability" patented technology

The invention belongs to the technical field of artificial intelligence and natural language processing, and discloses a persuasion skill-based automatic generation large model jailbreak prompt method. According to the method, multiple persuasion skills are combined with multiple persuasion skills such as logic persuasion, emotional persuasion and authoritative persuasion, so that the attack success rate is increased; and dynamically adjusting the attack strategy: adjusting the attack strategy in real time according to the attack progress and target model feedback, continuously optimizing the attack prompt, and adopting different jailbreak methods for different target large models. And finally generating a prompt which enables various large models to break prisons with high probability based on various persuasion skills and feedback of the target large model, and providing a new data set for security testing of the large models.

The security decentralized control method and system under the switching event trigger control strategy are a security decentralized control method of a networked interconnection large-scale system of the switching event trigger control strategy, and an event trigger mechanism ensures that the communication pressure of the system is effectively relieved when the system is subjected to external disturbance or denial of service attack. And the system can still keep stable operation and safety. Due to the property of an event triggering mechanism, a switchable event triggering mechanism is constructed and applied to each interconnected subsystem; and triggering a communication parameter through a collaborative design event, and controlling a rule through a safety controller. According to the invention, the interconnected large-scale system has # imgabs0 # performance level in response to denial of service and disturbance, the control performance can be ensured, and higher communication efficiency can be obtained. The method is suitable for safety control, communication optimization work and the like of an unmanned interconnection system and an intelligent power grid.

The invention provides a multi-feature fusion-based black box attack detection method (MFBA), device and system, different features are extracted by using a multi-model fusion strategy, the effectiveness and quality of opposite samples are improved, and the MFBA comprises the following three key steps: firstly, obtaining an initial data set from a target model; a decision boundary is approached by using a multi-feature fusion model; secondly, the stability of the model is enhanced through multiple rounds of training application data expansion and incremental learning technologies; and finally, generating opposite examples by using the optimized fusion model. By constructing the comprehensive attack framework, how to combine various model features to improve the performance against the resistance attack is demonstrated; compared with a single substitution model, the antagonism examples generated by the MFBA have higher mobility under different disturbance levels and have better attack effects; according to the method, an effective solution is provided for black box antagonism attacks, and the model in the generation of the advantage opposite paradigm of multi-feature fusion is verified.

The invention provides an AMADam-based adversarial sample generation method and system, and relates to the field of adversarial sample generation, and the specific scheme comprises the steps: preprocessing an obtained source image into an attacked image, and creating an all-zero tensor having the same shape as the attacked image; taking the all-zero tensor as initial disturbance, calculating an unbiased first moment and an unbiased second moment of the gradient by adopting an AMADam set momentum item method based on the gradient of the current disturbance in a loop iteration mode, generating new disturbance through the unbiased first moment and the unbiased second moment until the maximum iteration frequency is reached, and obtaining final disturbance; adding the final disturbance to an attacked image to generate an adversarial sample; according to the method, the AMADam algorithm is integrated into the gradient-based iterative attack, the unbiased first moment and the unbiased second moment of the gradient are used, disturbance is generated and updated for the attacked image, the adversarial sample is constructed, and the overall performance of the migration-based adversarial sample generation method is improved.

In order to solve the problem that the security of artificial intelligence technology is difficult to evaluate and improve in practical applications, the present invention provides a black box adversarial sample generation method based on the Transformer model, which belongs to the field of artificial intelligence technology. The main idea is to consider the impact of different coding blocks on the performance of adversarial samples, and classify the performance of coding blocks using coding block weight scores. Different strategies are used to generate adversarial samples for different coding blocks, balance the impact of image and model information on perturbations, stabilize the update direction of perturbations, and improve the attack success rate and migration ability of adversarial samples. Finally, adaptive weights are designed to adjust the perturbation size of key pixels, so that adversarial perturbations can improve attack capabilities without being noticeable to the human eye. The present invention significantly improves the migration ability of adversarial samples, can effectively evaluate and improve the security of artificial intelligence technology, and its experiments on image classification tasks fully demonstrate the effectiveness of the method.

The application discloses a PDC drill bit suitable for continuous and rapid drilling of a limestone stratum and application thereof. The drill bit comprises a drill bit body, the drill bit body is provided with a blade wing, and the blade wing is provided with cutting teeth arranged in double lines. The double lines comprise a main line and a secondary line, the main line and the secondary line are located on the same crown line, the main line is located on an infeed contact surface of the blade wing, and the secondary line is located behind the main line. The cutting teeth comprise plane teeth and flow-passing special-shaped cutting teeth, the main line is provided with main line plane teeth, and the secondary line is provided with flow-passing special-shaped cutting teeth. The flow-passing special-shaped cutting teeth are provided with a through tooth flow passage, and the blade wing is provided with a blade wing flow passage corresponding to the tooth flow passage. The application adopts the same crown line double line tooth arrangement, greatly reduces the impact force on the cutting teeth, and avoids early damage of the cutting teeth. The application is provided with the tooth flow passage and the blade wing flow passage, improves the cooling effect of the cutting teeth, avoids thermal damage of the cutting teeth, prolongs the service life of the cutting teeth, and ensures that the drill bit has continuous aggressiveness.

The present invention provides a PDC drill bit, which comprises: a core blade and an outer cone blade distributed around the circumference of the PDC drill bit, the core blade is provided with a diameter protection structure and a core mounting surface with a composite piece cutting tooth installed, and the outer cone blade is provided with a diameter protection structure and an outer cone mounting surface with a composite piece cutting tooth installed; the maximum outer diameter R of the outer contour of the core mounting surface max , and the minimum outer diameter R of the inner contour of the outer cone mounting surface min Satisfaction: R max ≤(0.9·R 保径 ), and R min ≥(0.3·R 保径 The present invention alleviates the technical problem that the PDC drill bit in the prior art is prone to tilt when drilling in soft formations, causing the wellbore inclination to exceed the standard.

The invention discloses a high-performance deep learning attack method for an asymmetric cryptographic system. The high-performance deep learning attack method comprises the following steps of: 1, encrypting an image by using a PTFT-based cryptographic system and an EMD-based cryptographic system respectively; 2, establishing plaintext-ciphertext pair data sets, and dividing each data set into a training set, a verification set and a test set which respectively comprise 600 pairs of plaintext-ciphertext data pairs, 200 pairs of plaintext-ciphertext data pairs and 200 pairs of plaintext-ciphertext data pairs; and a third step of designing a high-performance deep learning attack network RRU-NetPP, and training and debugging the network by using the established very small data set. And 4, attacking the ciphertext encrypted by the PTFT cryptosystem and the EMD cryptosystem by the established RRU-NetPP model, and retrieving the plaintext in real time with high quality. According to the method, the requirements on known plaintext-ciphertext data pairs can be remarkably reduced, the method has a few-sample learning capability, plaintexts can be retrieved from complex ciphertexts encrypted by different asymmetric cryptographic systems in real time in a high-quality manner, and the method has a strong attack capability.

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.

This invention discloses a robust aggregation method and system for federated learning based on multidimensional logs and deep reinforcement learning, applicable to federated learning systems including a server and multiple clients. The method includes: initializing a global model, a deep reinforcement learning agent, and an experience replay pool on the server side; sending the global model to each client and receiving local model updates; extracting multidimensional feature vectors and constructing a feature matrix through standardization and normalization; calculating the statistical moments of all client feature vectors, constructing a global state vector independent of the number of clients, inputting it into the agent's policy network to obtain an indicator weight vector; obtaining a corresponding comprehensive reputation score from the indicator weight vector and the feature vector of each client, introducing a temperature coefficient and normalizing it to obtain aggregation weights; weighted aggregation of the local model updates of all clients to update the global model; and updating the agent network parameters based on the accuracy of the new global model on the validation set as a reward signal.

The invention relates to the field of attack and defense confrontation of computer vision, in particular to a method for constructing a confrontation sample defense model based on image preprocessing, and the confrontation sample defense model comprises an auto-encoder for reconstructing a sample and an image classification model for classifying the reconstructed sample; the self-encoder adopts the clean samples to carry out autoregression training, and learns prior distribution of the clean samples; training of an image classification model: firstly, optimizing adversarial samples through an auto-encoder, then training the adversarial samples obtained through optimization, and enabling the adversarial samples to keep distribution closer to that of clean samples in manifold by incorporating distribution information of the clean samples into a training process; the problem caused by neglecting data distribution in the prior art is solved; in the confrontation and defense process, firstly, a sample is reconstructed through an auto-encoder, so that the attack intensity can be greatly weakened, and the robustness can be greatly improved. The method is suitable for various image classification fields, especially high-precision fields such as aerospace and the like.

The utility model provides a carbonatite and dolomite stratum oil well wire line coring tool, including drill stem, outer tube, inner tube, inner tube assembly, winch and fisher, drill stem bottom end is connected with outer tube, inner tube assembly is connected with inner tube top end, the free end of rope on winch is connected with fisher top end, outer tube bottom end is connected with PCD drill bit, and the outer tube bottom end is connected with the PCD drill bit. A through hole is formed in the central axis of the PCD drill bit, and the through hole is in butt joint with the rock core containing channel in the inner pipe; the PCD drill bit is provided with six straight blades, the width of each straight blade is 1 / 20-1 / 16 of the circumference of the PCD drill bit, each straight blade is provided with a plurality of cutting teeth, and on the same straight blade, the cutting teeth at the most front end are arranged on the end face of the bottom end of the through hole. The oil well wire-line coring tool for the carbonate rock and dolomite formations has the advantages of being high in drilling efficiency for the carbonate rock and dolomite formations, high in core yield rate for the unconsolidated sand shale of the Nadisk group and capable of being suitable for deep coring operation.

This invention discloses a method and system for generating adversarial examples based on multi-scale frequency domain decomposition, belonging to the field of artificial intelligence security. This invention relates to adversarial attacks and robustness evaluation techniques for deep learning models; by decomposing the input image into multiple frequency scale spaces, combining human visual perception characteristics with frequency domain sensitivity analysis of deep neural networks, adaptively applying targeted perturbations on different frequency bands, highly concealed and highly transferable adversarial examples are generated.

The application discloses a kind of spatiotemporal prediction model robustness test method, device, equipment and medium, by obtaining the traffic state and prediction label of the spatiotemporal traffic prediction model of the traffic network to be tested, establish the adversarial attack model of robustness test;According to the traffic state of the spatiotemporal traffic prediction model, the traffic label of the spatiotemporal traffic prediction model is estimated;According to the traffic label and the adversarial attack model, the significance of different nodes is calculated;According to the indicator function and the significance of different nodes, determine victim node;For victim node, generate local optimization after the adversarial sample of multiple-step iteration is carried out.It can produce dynamic adversarial sample to attack traffic spatiotemporal prediction model, only need to identify a small amount of victim node to test the robustness of traffic spatiotemporal prediction model, the adversarial sample generated has stronger attack, can fully test the robustness of traffic spatiotemporal prediction model.

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.