membership inference attack

Differentially Private Steering for Large Language Model Alignment ICLR 2025 DocMIA: Document-Level Membership Inference Attacks against DocVQA Models ICLR 2025 Does Data Contamination Detection Work (Well) for LLMs? A Survey and Evaluation on Detection Assumptions NAACL 2025 EverTracer: Hunting Stolen Large Language Models via Stealthy and Robust Probabilistic Fingerprint EMNLP 2025 Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment AISTATS 2025 Federated Graph Condensation with Information Bottleneck Principles AAAI 2025 FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning CVPR 2025 Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learning ICCV 2025 Fundamental Limits of Membership Inference Attacks on Machine Learning Models JMLR 2025 Identifying Unlearned Data in LLMs via Membership Inference Attacks EMNLP 2025 Membership Inference Attacks with False Discovery Rate Control ICCV 2025 MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector AAAI 2025 Multi-modal Identity Extraction ICCV 2025 OMS: One More Step Noise Searching to Enhance Membership Inference Attacks for Diffusion Models IJCAI 2025 On the Privacy Risks of Spiking Neural Networks: A Membership Inference Analysis UAI 2025 Personalized Language Models via Privacy-Preserving Evolutionary Model Merging EMNLP 2025 Privacy Attacks on Image AutoRegressive Models ICML 2025 Privacy-Preserving Low-Rank Adaptation Against Membership Inference Attacks for Latent Diffusion Models AAAI 2025 Public Data Assisted Differentially Private In-Context Learning EMNLP 2025 Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy IJCAI 2025 Safeguarding Privacy of Retrieval Data against Membership Inference Attacks: Is This Query Too Close to Home? EMNLP 2025 Sampling-based Pseudo-Likelihood for Membership Inference Attacks ACL 2025 Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models NAACL 2025 Some Targets Are Harder to Identify than Others: Quantifying the Target-dependent Membership Leakage AISTATS 2025 Speech Unlearning Interspeech 2025