AMAD: Improving Adversarial Robustness Without Reducing Accuracy -- Multi-Party Secure Sharing and Comparison of Strings Based on Outsourced Computation -- Highway: A Super Pipelined Parallel BFT Consensus Algorithm for Permissioned Blockchain -- Overview of DDoS Attack Research under SDN -- A medical image segmentation method based on Residual network and channel attention mechanism -- Performance improvement of classification model based on Chinese adversarial samples generation -- Research on Detection Method of Large-Scale Network Internal Attack Based on Machine Learning -- Federated Community Detection in Social Networks -- A Textual Adversarial Attack Scheme for Domain-Specific Models -- An improved Conv-LSTM method for gear fault detection -- Extracting Random Secret Key Scheme for One-time Pad under Intelligent Connected Vehicle -- Semi-supervised Learning with Nearest-Neighbor Label and Consistency Regularization -- Bipolar Picture Fuzzy Graph Based Multiple Attribute Decision Making Approach-Part I -- Priv-IDS: A Privacy Protection and Intrusion Detection Framework for In-Vehicle Network -- Dynamic Momentum for Deep Learning with Differential Privacy -- An Unsupervised Surface Anomaly Detection Method Based on Attention and ASPP -- PCB Defect Detection Method Based on Improved RetinaNet -- A Method of Protecting Sensitive Information in Intangible Cultural Heritage Communication Network Based on Machine Learning -- Decision Making Analysis of Traffic Accidents on Mountain Roads in Yunnan Province -- Deep Adaptively Feature Extracting Network for Cervical Squamous Lesion Cell Detection -- DSGRAE: Deep Sparse Graph Regularized Autoencoder for Anomaly Detection -- A Lattice-Based Aggregate Signature Based on Revocable Identity -- Research and design of an emergency supply assurance monitoring system in the post-epidemic context -- Face Presentation Attack Detection Based on Texture Gradient Enhancement and Multi-scale Fusion -- Optimal Revenue Analysis of the Stubborn Mining basedon Markov Decision Process -- Bipolar Picture Fuzzy Graph Based Multiple Attribute Decision Making Approach-Part II -- Machine Learning Based Method for Quantifying the Security Situation of Wireless Data Networks -- Overlapping community discovery algorithm based on three-level neighbor node influence -- Content-Aware Deep Feature Matching -- F2DLNet: A Face Forgery Detection and Localization Network Based on SSIM Error Maps -- An Eye-Gaze Tracking Method Based on a 3D Ocular Surface Fitting Model -- A Certificateless-Based Blind Signature Scheme with Message Recovery -- Fault Detection of Rolling Bearings by Using A Combination Network Model -- zkChain: An Efficient Blockchain Privacy Protection Scheme Based on zk-SNARKs -- Research on influential factors of online learning behavior based on big data -- Short speech key generation technology based on deep learning -- Domain Adversarial Interaction Network for Cross-domain Fault Diagnosis -- A Vehicle Data Publishing System with Privacy-awares inVANETs Based on Blockchain -- Highsimb: A Concrete Blockchain High Simulation With Contract Vulnerability Detection For Ethereum and Hyperledger Fabric -- Research on key technologies for the trusted perception of network information for big data -- Micro-expression Recognition Method Combining Dual-Stream Convolution and Capsule Network -- Security Scheduling Method of Cloud Network Big Data Cluster Based on Association Rule Algorithm -- Towards Differentially Private Contrastive Learning -- Two-stage High Precision Membership Inference Attack -- Secure Storage Method for Network Resources of professional Works Based on Decision Tree Algorithm -- Vehicle CAN Network Intrusion Detection Model Based on Extreme Learning Machine and Feature Analysis -- A Broad Learning System Based on the Idea of Vertical Federated Learning -- PAMP: A New Atomic Multi-Path Payments Method with Higher Routing Efficiency -- Privacy-Preserving Searchable Encryption Scheme Based on Deep Structured Semantic Model over Cloud Application -- A Event Extraction Method of Document-level based on the Self-attention Mechanism.

The three-volume proceedings set LNCS 13655,13656 and 13657 constitutes the refereed proceedings of the 4th International Conference on Machine Learning for Cyber Security, ML4CS 2022, which taking place during December 2-4, 2022, held in Guangzhou, China. The 100 full papers and 46 short papers were included in these proceedings were carefully reviewed and selected from 367 submissions.