Privacy

User-level Differentially Private Stochastic Convex Optimization: Efficient Algorithms with Optimal Rates AISTATS 2024 VA3: Virtually Assured Amplification Attack on Probabilistic Copyright Protection for Text-to-Image Generative Models CVPR 2024 Validating Privacy-Preserving Face Recognition under a Minimum Assumption CVPR 2024 VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models ICLR 2024 VFLAIR: A Research Library and Benchmark for Vertical Federated Learning ICLR 2024 Vision-Language Models are Strong Noisy Label Detectors NeurIPS 2024 WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection ACL 2024 Wasserstein Differential Privacy AAAI 2024 Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents NeurIPS 2024 Waterfall: Scalable Framework for Robust Text Watermarking and Provenance for LLMs EMNLP 2024 WateRF: Robust Watermarks in Radiance Fields for Protection of Copyrights CVPR 2024 Watermarking Conditional Text Generation for AI Detection: Unveiling Challenges and a Semantic-Aware Watermark Remedy AAAI 2024 Watermarking Makes Language Models Radioactive NeurIPS 2024 WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off NeurIPS 2024 WatME: Towards Lossless Watermarking Through Lexical Redundancy ACL 2024 What makes unlearning hard and what to do about it NeurIPS 2024 What's In My Big Data? ICLR 2024 When Fairness Meets Privacy: Exploring Privacy Threats in Fair Binary Classifiers via Membership Inference Attacks IJCAI 2024 Where Am I From? Identifying Origin of LLM-generated Content EMNLP 2024 Would You Like Your Data to Be Trained? A User Controllable Recommendation Framework AAAI 2024 You Only Query Once: An Efficient Label-Only Membership Inference Attack ICLR 2024 ZeroMark: Towards Dataset Ownership Verification without Disclosing Watermark NeurIPS 2024 Zombie: Middleboxes that Don’t Snoop NSDI 2024 A Blessing of Dimensionality in Membership Inference through Regularization AISTATS 2023 Accountable authentication with privacy protection: The Larch system for universal login OSDI 2023