Privacy

Trap-MID: Trapdoor-based Defense against Model Inversion Attacks NeurIPS 2024 TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification ACL 2024 Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense NeurIPS 2024 Ungeneralizable Examples CVPR 2024 Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement NeurIPS 2024 United We Stand, Divided We Fall: Fingerprinting Deep Neural Networks via Adversarial Trajectories NeurIPS 2024 Universally Instance-Optimal Mechanisms for Private Statistical Estimation COLT 2024 Unlearning during Learning: An Efficient Federated Machine Unlearning Method IJCAI 2024 Unlearning Traces the Influential Training Data of Language Models ACL 2024 Unlocking Memorization in Large Language Models with Dynamic Soft Prompting EMNLP 2024 Vaccine: Perturbation-aware Alignment for Large Language Models against Harmful Fine-tuning Attack NeurIPS 2024 Waterfall: Scalable Framework for Robust Text Watermarking and Provenance for LLMs EMNLP 2024 Watermarking for Large Language Models ACL 2024 WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off NeurIPS 2024 Where Am I From? Identifying Origin of LLM-generated Content EMNLP 2024 Who Wrote this Code? Watermarking for Code Generation ACL 2024 Your Transferability Barrier is Fragile: Free-Lunch for Transferring the Non-Transferable Learning CVPR 2024 A Blessing of Dimensionality in Membership Inference through Regularization AISTATS 2023 A Customized Text Sanitization Mechanism with Differential Privacy ACL 2023 Algorithms for bounding contribution for histogram estimation under user-level privacy ICML 2023 Anti-DreamBooth: Protecting Users from Personalized Text-to-image Synthesis ICCV 2023 Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark ACL 2023 A Smooth Binary Mechanism for Efficient Private Continual Observation NeurIPS 2023 Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks EMNLP 2023 Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger NeurIPS 2023