Security & Privacy

Balls-and-Bins Sampling for DP-SGD AISTATS 2025 Best Linear Unbiased Estimate from Privatized Contingency Tables JMLR 2025 Beyond De-Identification: A Structured Approach for Defining and Detecting Indirect Identifiers in Medical Texts NAACL 2025 Beyond Text: Unveiling Privacy Vulnerabilities in Multi-modal Retrieval-Augmented Generation EMNLP 2025 Black-Box Forgery Attacks on Semantic Watermarks for Diffusion Models CVPR 2025 BrainGuard: Privacy-Preserving Multisubject Image Reconstructions from Brain Activities AAAI 2025 Breaking ReAct Agents: Foot-in-the-Door Attack Will Get You In NAACL 2025 Break the Breakout: Reinventing LM Defense Against Jailbreak Attacks with Self-Refine NAACL 2025 CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference ACL 2025 Characterizing the Accuracy-Communication-Privacy Trade-off in Distributed Stochastic Convex Optimization AISTATS 2025 Children's Voice Privacy: First Steps and Emerging Challenges Interspeech 2025 ClaritySpeech: Dementia Obfuscation in Speech Interspeech 2025 Classifier-Free Guidance Inside the Attraction Basin May Cause Memorization CVPR 2025 CLEAR: Character Unlearning in Textual and Visual Modalities ACL 2025 CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing EMNLP 2025 Combating Phone Scams with LLM-based Detection: Where Do We Stand? (Student Abstract) AAAI 2025 Compass: Encrypted Semantic Search with High Accuracy OSDI 2025 ConcreTizer: Model Inversion Attack via Occupancy Classification and Dispersion Control for 3D Point Cloud Restoration ICLR 2025 Controlled Generation for Private Synthetic Text EMNLP 2025 Convergent Privacy Loss of Noisy-SGD without Convexity and Smoothness ICLR 2025 CopyrightShield: Enhancing Diffusion Model Security Against Copyright Infringement Attacks ICCV 2025 Counterfactual Evaluation for Blind Attack Detection in LLM-based Evaluation Systems IJCNLP 2025 Counting Graphlets of Size k under Local Differential Privacy AISTATS 2025 Crossfire: An Elastic Defense Framework for Graph Neural Networks Under Bit Flip Attacks AAAI 2025 Crypto-LLM: Two-Stage Language Model Pre-training with Ciphered and Natural Language Data IJCNLP 2025