Security & Privacy

Privacy-Preserving Optics for Enhancing Protection in Face De-Identification CVPR 2024 Private and Personalized Frequency Estimation in a Federated Setting NeurIPS 2024 Private Edge Density Estimation for Random Graphs: Optimal, Efficient and Robust NeurIPS 2024 Private Geometric Median NeurIPS 2024 Private Language Models via Truncated Laplacian Mechanism EMNLP 2024 Private prediction for large-scale synthetic text generation EMNLP 2024 Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions NeurIPS 2024 Private Zeroth-Order Nonsmooth Nonconvex Optimization ICLR 2024 PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques NeurIPS 2024 Probabilistically Robust Watermarking of Neural Networks IJCAI 2024 Prompt Leakage effect and mitigation strategies for multi-turn LLM Applications EMNLP 2024 Protecting Object Detection Models from Model Extraction Attack via Feature Space Coverage IJCAI 2024 Protect Your Score: Contact-Tracing with Differential Privacy Guarantees AAAI 2024 PSILENCE: A Pseudonymization Tool for International Law EACL 2024 Public-data Assisted Private Stochastic Optimization: Power and Limitations NeurIPS 2024 Publishing Number of Walks and Katz Centrality under Local Differential Privacy UAI 2024 ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods EMNLP 2024 Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models EMNLP 2024 Reimagining Mutual Information for Enhanced Defense against Data Leakage in Collaborative Inference NeurIPS 2024 Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective AAAI 2024 Resource Efficient Deep Learning Hardware Watermarks with Signature Alignment AAAI 2024 Responsible Bandit Learning via Privacy-Protected Mean-Volatility Utility AAAI 2024 Rethinking LLM Memorization through the Lens of Adversarial Compression NeurIPS 2024 Revisiting Differentially Private ReLU Regression NeurIPS 2024 Revisiting the Robustness of Watermarking to Paraphrasing Attacks EMNLP 2024