Security & Privacy

Fully Decentralized Certified Unlearning CVPR 2026 Hyperion: Private Token Sampling with Homomorphic Encryption ACL 2026 Imprecise Probabilities for Privacy–Accuracy Trade-offs in Bayesian Networks UAI 2026 Improved Regret in Stochastic Decision-Theoretic Online Learning under Differential Privacy ALT 2026 Improving the Convergence of Private Shuffled Gradient Methods with Public Data UAI 2026 Invited Open Problem: Does Differential Privacy Make PAC Learning Much Harder? COLT 2026 JANUS: Cross-World, Cooperative Nested Virtualization for Secure Containers OSDI 2026 LDP-Slicing: Local Differential Privacy for Images via Randomized Bit-Plane Slicing CVPR 2026 Minimax density estimation in the adversarial framework under local differential privacy JMLR 2026 Minimax optimal differentially private synthetic data for smooth queries COLT 2026 Mitigating Backdoor Attacks via Trigger Reconstruction and Model Hardening WACV 2026 Nearly Linear-Time User-Level DP-SCO with Optimal Rates COLT 2026 Nested SEV: Secure and Generic SEV Support for Nested Virtualization OSDI 2026 On Purely Private Covariance Estimation ALT 2026 On the Curse of Dimensionality in Private Sparse Covariance Estimation and PCA COLT 2026 Osprey: Transparent and Efficient Virtual Memory for Secure Computation OSDI 2026 Overcoming Copyright Barriers in Corpus Distribution Through Non-Reversible Hashing ACL 2026 Over-Threshold Multiparty Private Set Intersection for Collaborative Network Intrusion Detection NSDI 2026 PDR: A Plug-and-Play Positional Decay Framework for LLM Pre-training Data Detection ACL 2026 PECCVAI: Overcoming the Brittleness of AI Image Watermarking Under Visual Paraphrasing Attacks CVPR 2026 Personalized Federated Training of Diffusion Models with Privacy Guarantees CVPR 2026 Powerful Training-Free Membership Inference Against Fine-Tuned Autoregressive Language Models ACL 2026 Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models ACL 2026 Privacy-Preserving Robustness Verification for Neural Networks UAI 2026 Privacy-R1: Privacy-Aware Multi-LLM Agent Collaboration via Reinforcement Learning ACL 2026