Security & Privacy

CTCC: A Robust and Stealthy Fingerprinting Framework for Large Language Models via Cross-Turn Contextual Correlation Backdoor EMNLP 2025 CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications IJCNLP 2025 Cutting Through Privacy: A Hyperplane-Based Data Reconstruction Attack in Federated Learning UAI 2025 Data Reconstruction Attacks and Defenses: A Systematic Evaluation AISTATS 2025 Decoder Gradient Shield: Provable and High-Fidelity Prevention of Gradient-Based Box-Free Watermark Removal CVPR 2025 Defending Unauthorized Voice Cloning with Watermark-Aware Codecs Interspeech 2025 Defense Against Model Stealing Based on Account-Aware Distribution Discrepancy AAAI 2025 Defense Against Prompt Injection Attack by Leveraging Attack Techniques ACL 2025 Deriving Semantic Checkers from Tests to Detect Silent Failures in Production Distributed Systems OSDI 2025 Differentially private algorithms for linear queries via stochastic convex optimization AISTATS 2025 Differentially Private Bootstrap: New Privacy Analysis and Inference Strategies JMLR 2025 Differentially Private Continual Release of Histograms and Related Queries AISTATS 2025 Differentially Private Fine-Tuning of Diffusion Models ICCV 2025 Differentially Private Graph Data Release: Inefficiencies & Unfairness AISTATS 2025 Differentially Private Integrated Decision Gradients (IDG-DP) for Radar-Based Human Activity Recognition WACV 2025 Differentially Private Multivariate Medians JMLR 2025 Differentially Private Prototypes for Imbalanced Transfer Learning AAAI 2025 Differentially Private Range Queries with Correlated Input Perturbation AISTATS 2025 Differential Privacy in Distributed Learning: Beyond Uniformly Bounded Stochastic Gradients AISTATS 2025 Differential Private Stochastic Optimization with Heavy-tailed Data: Towards Optimal Rates AAAI 2025 Distribution-Aware Mean Estimation under User-level Local Differential Privacy AISTATS 2025 Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgetting AAAI 2025 DOMBA: Double Model Balancing for Access-Controlled Language Models via Minimum-Bounded Aggregation AAAI 2025 DPED: Multi-Layer Noise Distillation for Privacy-Preserving Text Embeddings EMNLP 2025 DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models AAAI 2025