Security & Privacy

Invisible Backdoor Attack against Self-supervised Learning CVPR 2025 ISACL: Internal State Analyzer for Copyrighted Training Data Leakage EMNLP 2025 “I’ve Decided to Leak”: Probing Internals Behind Prompt Leakage Intents EMNLP 2025 Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguising CVPR 2025 Jailbreaking with Universal Multi-Prompts NAACL 2025 Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering EMNLP 2025 Knockoff Branch: Model Stealing Attack via Adding Neurons in the Pre-Trained Model WACV 2025 Label-Free Backdoor Attacks in Vertical Federated Learning AAAI 2025 Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysis NAACL 2025 Learning from End User Data with Shuffled Differential Privacy over Kernel Densities ICLR 2025 Learning Robust and Privacy-Preserving Representations via Information Theory AAAI 2025 Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guarantees EMNLP 2025 LiD-FL: Towards List-Decodable Federated Learning AAAI 2025 Locally Private Estimation with Public Features AISTATS 2025 Locally Private Sampling with Public Data AISTATS 2025 LongSafety: Evaluating Long-Context Safety of Large Language Models ACL 2025 LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty CVPR 2025 Low-Rank Adaptation in Multilinear Operator Networks for Security-Preserving Incremental Learning CVPR 2025 MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol EMNLP 2025 MEDUSA: Medical Data Under Shadow Attacks via Hybrid Model Inversion AISTATS 2025 Membership and Memorization in LLM Knowledge Distillation EMNLP 2025 Membership Inference Attacks with False Discovery Rate Control ICCV 2025 MEraser: An Effective Fingerprint Erasure Approach for Large Language Models ACL 2025 Merger-as-a-Stealer: Stealing Targeted PII from Aligned LLMs with Model Merging EMNLP 2025 Mesh Watermark Removal Attack and Mitigation: A Novel Perspective of Function Space AAAI 2025