privacy leakage

Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion Attacks ICLR 2025 SynthTextEval: Synthetic Text Data Generation and Evaluation for High-Stakes Domains EMNLP 2025 The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD ICLR 2025 TrojanStego: Your Language Model Can Secretly Be A Steganographic Privacy Leaking Agent EMNLP 2025 Underestimated Privacy Risks for Minority Populations in Large Language Model Unlearning ICML 2025 Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems NAACL 2025 WavShape: Information-Theoretic Speech Representation Learning for Fair and Privacy-Aware Audio Processing Interspeech 2025 Analysis of Privacy Leakage in Federated Large Language Models AISTATS 2024 Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks ICLR 2024 Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approach NeurIPS 2024 Chronic Poisoning: Backdoor Attack against Split Learning AAAI 2024 FedInverse: Evaluating Privacy Leakage in Federated Learning ICLR 2024 Foreseeing Reconstruction Quality of Gradient Inversion: An Optimization Perspective AAAI 2024 Integer Is Enough: When Vertical Federated Learning Meets Rounding AAAI 2024 Measuring Dejavu Memorization Efficiently NeurIPS 2024 Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy NeurIPS 2024 Mitigating Privacy Seesaw in Large Language Models: Augmented Privacy Neuron Editing via Activation Patching ACL 2024 MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models NeurIPS 2024 PANORAMIA: Privacy Auditing of Machine Learning Models without Retraining NeurIPS 2024 Poincaré Differential Privacy for Hierarchy-Aware Graph Embedding AAAI 2024 Position: Towards Implicit Prompt For Text-To-Image Models ICML 2024 Practical Privacy-Preserving MLaaS: When Compressive Sensing Meets Generative Networks AAAI 2024 Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models NeurIPS 2024 PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action NeurIPS 2024 PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques NeurIPS 2024