6results about How to "Improve attack ability" patented technology

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.

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 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.