Privacy

Which Retain Set Matters for LLM Unlearning? A Case Study on Entity Unlearning ACL 2025 With Privacy, Size Matters: On the Importance of Dataset Size in Differentially Private Text Rewriting IJCNLP 2025 Zero-Shot Class Unlearning in CLIP with Synthetic Samples WACV 2025 ZIUM: Zero-Shot Intent-Aware Adversarial Attack on Unlearned Models ICCV 2025 pfl-research: simulation framework for accelerating research in Private Federated Learning NeurIPS 2024 A2XP: Towards Private Domain Generalization CVPR 2024 AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents NeurIPS 2024 A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy NeurIPS 2024 An Inversion Attack Against Obfuscated Embedding Matrix in Language Model Inference EMNLP 2024 A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learning CVPR 2024 Auditing Privacy Mechanisms via Label Inference Attacks NeurIPS 2024 Authorship Obfuscation in Multilingual Machine-Generated Text Detection EMNLP 2024 Backdoor Federated Learning by Poisoning Backdoor-Critical Layers ICLR 2024 Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs NeurIPS 2024 Beyond Slow Signs in High-fidelity Model Extraction NeurIPS 2024 Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature NeurIPS 2024 Can LLMs get help from other LLMs without revealing private information? ACL 2024 Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory ICLR 2024 Can Simple Averaging Defeat Modern Watermarks? NeurIPS 2024 Center-Based Relaxed Learning Against Membership Inference Attacks UAI 2024 CERT-ED: Certifiably Robust Text Classification for Edit Distance EMNLP 2024 Code Membership Inference for Detecting Unauthorized Data Use in Code Pre-trained Language Models EMNLP 2024 Collaborative Synthesis of Patient Records through Multi-Visit Health State Inference AAAI 2024 Concealing Sensitive Samples against Gradient Leakage in Federated Learning AAAI 2024 Correlated Noise Provably Beats Independent Noise for Differentially Private Learning ICLR 2024