14 results about "Classful network" patented technology

The application discloses a contract attack detection method and device based on symbolic execution and a graph neural network, comprising: obtaining deployment bytecode and runtime bytecode of a smart contract; performing symbolic execution on the runtime bytecode, extracting external calls and event information through depth-first search and taint tracking; constructing a contract call information graph and iteratively simplifying it; performing multi-dimensional feature coding on each node to generate a node feature vector; encoding on-chain metadata of a deployer into a deployer feature vector; constructing and training a graph embedding network and a classification network, the input of the graph embedding network being the simplified contract call information graph, the node feature vector and edge type information, and the output being a graph-level feature vector; the input of the classification network being a joint feature vector obtained by splicing the graph-level feature vector and the deployer feature vector, and the output being a contract classification result. The application can cover multiple attack types and realize attack contract identification with low false alarm rate by extracting contract execution logic structures for detection.

The application discloses a kind of based on IDC-Net network's ceramic tile product surface defect classification method and system, belong to ceramic tile surface defect classification technical field, including.The application designs the basic unit IDC-Block with feature enhancement capability, the module integrates dynamic large kernel convolution DLK and inherits the advantage of efficient feature extraction of visual state space block VSSBlock IDC-Layer is constituted, on the basis of IDC-Layer, dense connection design is used to constitute IDC-Block by multilevel structure stacking, gradually enhanced feature representation ability;Further design adaptive gaussian pooling module AGP, reduce the information loss in down-sampling process, significantly improve the classification performance of model to ceramic tile small target defect;Dynamic feature fusion module DYFF is designed, adaptive fusion of different resolution and semantic level features is realized, and the robustness of feature expression is enhanced;With EfficientNetV2-s classification network framework as auxiliary branch, local and global information is integrated to constitute double-path classification network IDC-Net by DYFF module, and the classification accuracy is further improved.

This invention discloses a three-dimensional breast ABUS image classification method, electronic device, and computer-readable storage medium based on a tokenized bi-branch selective state-space model. The method preprocesses the three-dimensional ABUS volume data and inputs it into a hierarchical pyramidal classification network. The network constructs local convolutional branches and a global state-space branch in its basic modules: the local branch uses lightweight three-dimensional grouped convolution to extract texture and boundary morphology; the global branch aggregates features into a token map through voxel token generation, then performs multi-axis bi-directional selective state-space scanning and adaptive fusion using routing weights. After detoxing, the core features are injected through a gating mechanism. Finally, the classification result is output through three-dimensional global average pooling and a fully connected layer, enhancing the ability to model long-range dependencies across slices with near-linear complexity.

The application provides a power equipment state diagnosis method and device based on multi-source data fusion and a terminal equipment, and belongs to the technical field of power equipment state diagnosis. The method comprises the following steps: acquiring image, text and running sound data of power equipment, and inputting the data into a detection model comprising an image, text, sound backbone network, multi-modal feature fusion network and target classification network. Visual, semantic and audio features are respectively extracted by using each backbone network, multi-modal feature standardization vectors are generated, adaptive weight fusion is performed on the multi-modal feature standardization vectors by using the multi-modal feature fusion network to obtain multi-modal fusion features, and finally, the fusion features are identified by using the target classification network to output the type and state diagnosis result of the power equipment. The application can solve the problem of the existing technology that the detection accuracy decreases and misjudgment and missed judgment easily occur in a complex and low-light scene.

This invention discloses a lightweight method for deep classification networks of distillate oils. Based on the Conformer-1D convolutional-attention fusion network, it addresses the problems of large model size and slow inference in industrial deployments by employing structured pruning based on channel importance for convolutional branches and using singular value decomposition for low-rank approximation of the core weights of attention branches. Furthermore, post-training quantization compresses the 32-bit floating-point weights into 8-bit integers. This invention significantly reduces the number of model parameters and storage requirements while improving inference speed, under the premise of controllable loss in classification accuracy. This enables high-precision distillate oil classification models to be efficiently deployed in resource-constrained environments such as embedded systems and edge computing, demonstrating strong engineering application value.

The application discloses a network intrusion detection method based on mixed sampling and multi-scale attention fusion, belongs to the field of network intrusion detection, and comprises the following steps: traffic data class equalization based on mixed sampling; time-frequency feature mapping based on continuous wavelet transform; spatial feature extraction and fusion based on multi-scale convolution; and weight self-adaptive adjustment based on a channel attention mechanism; enhanced deep features are input into a trained multi-scale attention classification network, and prediction probability distribution of each dimension is output, so that accurate classification of network intrusion behaviors is realized. The application uses a mixed sampling scheme of random undersampling and a conditional generative adversarial network to solve the problem of class imbalance of an original data set, uses continuous wavelet transform to mine hidden patterns of traffic features, solves the problem of insufficient representation of original traffic data, uses multi-scale convolution and channel attention to improve recognition accuracy, and solves the problem of insufficient spatial feature extraction.

This invention discloses a packet classification processing system based on the joint compilation of multi-mode DFA automata, comprising: a feature extraction module for extracting the state transition path features of each independent DFA automaton participating in the joint compilation and the features of the network packets to be classified; an integrated compilation core module that integrates a quantum hash processing unit and a biological sequence alignment processing unit to achieve collaborative compilation of path optimization and index construction; and a global homogeneous path sharing pool for storing path-related data output by the integrated compilation core module, enabling the reuse of homogeneous path segments among multiple DFAs. This invention, through the collaborative work of quantum hash processing and biological sequence alignment, accurately identifies and reuses homogeneous path segments in multi-mode DFAs, avoiding the repeated storage and computation of paths caused by traditional independent compilation, significantly reducing the overall redundancy of the state machine, improving storage and computation efficiency, and enhancing matching accuracy and reliability.

The application discloses an intelligent contract vulnerability detection method combining adversarial transfer learning and multi-task learning. First, in the data preprocessing stage, the operation code sequence formed by the decompilation of the intelligent contract sample source code is processed by using an N-Gram language model to construct a 2-gram operation code syntax sequence, and the input of the model is formed. Secondly, in the model construction stage, a bottom shared layer based on a mixed parameter sharing architecture design is constructed to extract general features and private features; a top task layer of a multi-task classification network based on a neural network is constructed to realize the detection and identification tasks of the intelligent contract vulnerability; and finally, the intelligent contract vulnerability detection model is constructed by combining adversarial transfer learning and multi-task learning. In the training stage, the 2-gram operation code syntax sequence obtained in the data preprocessing stage is input into the model for training, and the application has good generalization performance.

The application relates to the technical field of satellite communication and discloses an open domain radiation source individual identification method and system based on deep learning, which comprises the following steps: acquiring a monitoring signal of a communication satellite and pre-processing the monitoring signal; inputting the pre-processed monitoring signal into a deep learning network for feature extraction to obtain a deep feature vector; training an individual identification classification network based on the deep feature vector; in the training process, a decision threshold value of an open set and a closed set is determined by combining a prediction score output of known category and unknown category data with an open set classification rate calculation criterion; the to-be-tested monitoring signal is pre-processed and feature-extracted, and a prediction score is output by using the trained individual identification classification network; the maximum value of the prediction score is compared with the decision threshold value; if the maximum value of the prediction score is greater than or equal to the decision threshold value, a corresponding known category label is output; otherwise, an unknown category label is output. The application improves the identification accuracy of unknown categories under the premise of ensuring the closed set performance.

This application relates to the technical field, specifically to a real-time detection method for DNS tunneling attacks based on an LSTM-Transformer hybrid architecture, comprising the following steps: Step 1: Collecting continuous DNS data streams from the network and extracting the original DNS query sequence as input features; Step 2: Constructing a hybrid neural network architecture consisting of a temporal feature extraction module and a global dependency modeling module; Step 3: An information fusion module fuses temporal feature vectors and long-distance dependency feature vectors to generate a joint representation vector; Step 4: A classification network model classifies attack behaviors based on the joint representation vector and outputs the detection results of DNS tunneling attacks in real time. This method, through the collaborative extraction of deep temporal patterns and global dependency features of DNS query sequences using an LSTM-Transformer hybrid architecture, can accurately model the inherent DNS protocol behavior patterns of network nodes.

The application belongs to the technical field of computer data processing, and relates to a management system supporting real-time convergence and intelligent classification of multi-store orders, which comprises: a monitoring and strategy generation module that acquires global operation state parameters and generates adaptive coding strategy instructions according to a business scene model; an edge collection module that captures original order messages and extracts a target key field set according to the instructions; an edge coding module that codes the field set to generate a variable-structure order feature vector; a receiving and loading module that receives the vector and activates a matching target decoding head model; a decoding restoration module that generates a standardized decision feature tensor by using the model; a classification calculation module that outputs intelligent classification result labels by using a multi-level classification network; and a feedback and updating module that executes business control logic and updates parameters. The application solves the problem of dynamically adjusting edge data processing strategies according to real-time system states in the multi-store order processing scene to balance data processing accuracy and system resource consumption.

The present application belongs to the technical field of fire prediction, and relates to a parking lot fire prediction method. The method positions a fire area through class activation mapping based on semantic features, and uses a cross-generation feature aggregation module to aggregate iterative output results based on network intermediate layer multi-scale features and results output during a training process. Meanwhile, the method fuses an original RGB input picture based on an initial rough segmentation result, and inputs the picture into a classification network for secondary fine segmentation, which can reduce a false positive rate, is not affected by a surrounding environment, has low data requirements, and can only be used in the field of parking lot fire detection, and is also applicable to other fields with insufficient data sets and requiring a weak supervision mode to improve precision.

This invention relates to a method for detecting network traffic anomalies with few samples. The method includes the following steps: S1, constructing a dual-domain traffic feature space to obtain dual-modal data; S2, using the dual-modal data as input, constructing and training a Siamese neural network based on the Mamba architecture, with the Siamese neural network outputting support set features and query set features; S3, calculating the topological confidence of the support set samples; S4, performing asymmetric weighted modulation on the support set features and query set features based on the topological confidence to obtain a fused feature vector; S5, inputting the fused feature vector into a classification network to obtain anomaly detection results, and performing incremental learning based on the anomaly detection results. Compared with existing technologies, this invention has advantages such as achieving high-precision intrusion detection under limited sample conditions.