Privacy

Can LLM Watermarks Robustly Prevent Unauthorized Knowledge Distillation? ACL 2025 Can Private Machine Learning Be Fair? AAAI 2025 Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data? AAAI 2025 CAPTURE: Context-Aware Prompt Injection Testing and Robustness Enhancement ACL 2025 CBP-Tuning: Efficient Local Customization for Black-box Large Language Models EMNLP 2025 CDI: Copyrighted Data Identification in Diffusion Models CVPR 2025 CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference ACL 2025 Certified Machine Unlearning Under High Dimensional Regime JMLR 2025 Classifier-Free Guidance Inside the Attraction Basin May Cause Memorization CVPR 2025 CLEAR: Character Unlearning in Textual and Visual Modalities ACL 2025 CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP ACL 2025 CLIPure: Purification in Latent Space via CLIP for Adversarially Robust Zero-Shot Classification ICLR 2025 CLMTracing: Black-box User-level Watermarking for Code Language Model Tracing EMNLP 2025 CluSanT: Differentially Private and Semantically Coherent Text Sanitization NAACL 2025 CollabEdit: Towards Non-destructive Collaborative Knowledge Editing ICLR 2025 Community-Centric Graph Unlearning AAAI 2025 Compass: Encrypted Semantic Search with High Accuracy OSDI 2025 ConceptPrune: Concept Editing in Diffusion Models via Skilled Neuron Pruning ICLR 2025 ConFREE: Conflict-free Client Update Aggregation for Personalized Federated Learning AAAI 2025 Context-Aware Membership Inference Attacks against Pre-trained Large Language Models EMNLP 2025 Controllable Memorization in LLMs via Weight Pruning EMNLP 2025 Controllable Unlearning for Image-to-Image Generative Models via ε-Constrained Optimization ICLR 2025 Controlled Generation for Private Synthetic Text EMNLP 2025 Copyright Infringement by Large Language Models in the EU: Misalignment, Safeguards, and the Path Forward EMNLP 2025 CopyrightShield: Enhancing Diffusion Model Security Against Copyright Infringement Attacks ICCV 2025