Privacy

Provable Mutual Benefits from Federated Learning in Privacy-Sensitive Domains AISTATS 2024 Proving membership in LLM pretraining data via data watermarks ACL 2024 Pseudonymization Categories across Domain Boundaries COLING 2024 Pseudo-Private Data Guided Model Inversion Attacks NeurIPS 2024 PSILENCE: A Pseudonymization Tool for International Law EACL 2024 Psychological Assessments with Large Language Models: A Privacy-Focused and Cost-Effective Approach EACL 2024 Public-data Assisted Private Stochastic Optimization: Power and Limitations NeurIPS 2024 Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes ACL 2024 Pure Differential Privacy for Functional Summaries with a Laplace-like Process JMLR 2024 PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics NeurIPS 2024 Purified and Unified Steganographic Network CVPR 2024 Putting Context in Context: the Impact of Discussion Structure on Text Classification EACL 2024 Quantifying and Analyzing Entity-Level Memorization in Large Language Models AAAI 2024 Quantifying Unintended Memorization in BEST-RQ ASR Encoders Interspeech 2024 RAFT: Realistic Attacks to Fool Text Detectors EMNLP 2024 Ransom Access Memories: Achieving Practical Ransomware Protection in Cloud with DeftPunk OSDI 2024 RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees NeurIPS 2024 ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods EMNLP 2024 Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable NeurIPS 2024 Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models EMNLP 2024 RedCode: Risky Code Execution and Generation Benchmark for Code Agents NeurIPS 2024 Reducing Privacy Risks in Online Self-Disclosures with Language Models ACL 2024 Reimagining Mutual Information for Enhanced Defense against Data Leakage in Collaborative Inference NeurIPS 2024 Representation Noising: A Defence Mechanism Against Harmful Finetuning NeurIPS 2024 Responsible Bandit Learning via Privacy-Protected Mean-Volatility Utility AAAI 2024