Privacy

Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models NAACL 2025 SDD: Self-Degraded Defense against Malicious Fine-tuning ACL 2025 Security Attacks on LLM-based Code Completion Tools AAAI 2025 SelectFormer in Data Markets: Privacy-Preserving and Efficient Data Selection for Transformers with Multi-Party Computation ICLR 2025 Sibai: A Few-Shot Meta-Classifier for Poisoning Detection in Federated Learning ICCV 2025 Silence is Golden: Leveraging Adversarial Examples to Nullify Audio Control in LDM-based Talking-Head Generation CVPR 2025 Some Targets Are Harder to Identify than Others: Quantifying the Target-dependent Membership Leakage AISTATS 2025 Speed Master: Quick or Slow Play to Attack Speaker Recognition AAAI 2025 Split Adaptation for Pre-trained Vision Transformers CVPR 2025 Stealing Training Data from Large Language Models in Decentralized Training through Activation Inversion Attack ACL 2025 Stealthy Backdoor Attack in Federated Learning via Adaptive Layer-wise Gradient Alignment ICCV 2025 Stealthy Backdoor Attack in Self-Supervised Learning Vision Encoders for Large Vision Language Models CVPR 2025 Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks ICLR 2025 StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data ICCV 2025 SUA: Stealthy Multimodal Large Language Model Unlearning Attack EMNLP 2025 T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation CVPR 2025 TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity ICCV 2025 Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization EMNLP 2025 The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD ICLR 2025 Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems CVPR 2025 Towards Privacy-Preserving Split Learning for ControlNet WACV 2025 Towards Secure User Authentication for Headphones via In-Ear or In-Earcup Microphones Interspeech 2025 Tracing Training Footprints: A Calibration Approach for Membership Inference Attacks Against Multimodal Large Language Models EMNLP 2025 Training Data Provenance Verification: Did Your Model Use Synthetic Data from My Generative Model for Training? CVPR 2025 TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent EMNLP 2025