Privacy

Model Equality Testing: Which Model is this API Serving? ICLR 2025 Model Rake: A Defense Against Stealing Attacks in Split Learning IJCAI 2025 Model Unlearning via Sparse Autoencoder Subspace Guided Projections EMNLP 2025 Moderating the Generalization of Score-based Generative Model ICCV 2025 Mr. Snuffleupagus at SemEval-2025 Task 4: Unlearning Factual Knowledge from LLMs Using Adaptive RMU SemEval 2025 MULTIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities EMNLP 2025 Multi-modal Identity Extraction ICCV 2025 Multimodal Pragmatic Jailbreak on Text-to-image Models ACL 2025 Multi-Modal Recommendation Unlearning for Legal, Licensing, and Modality Constraints AAAI 2025 MUSE: Machine Unlearning Six-Way Evaluation for Language Models ICLR 2025 MYOPIA: Protecting Face Privacy from Malicious Personalized Text-to-Image Synthesis via Unlearnable Examples AAAI 2025 NAP2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human EMNLP 2025 Navigating Heterogeneity and Privacy in One-Shot Federated Learning with Diffusion Models WACV 2025 Near-Exact Privacy Amplification for Matrix Mechanisms ICLR 2025 Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models CVPR 2025 NEKO at SemEval-2025 Task 4: A Gradient Ascent Based Machine Unlearning Strategy SemEval 2025 NLPART at SemEval-2025 Task 4: Forgetting is harder than Learning SemEval 2025 NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning AAAI 2025 Not Every Token Needs Forgetting: Selective Unlearning Balancing Forgetting and Utility in Large Language Models EMNLP 2025 NoT: Federated Unlearning via Weight Negation CVPR 2025 Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models CVPR 2025 Not What the Doctor Ordered: Surveying LLM-based De-identification and Quantifying Clinical Information Loss EMNLP 2025 ObfusLM: Privacy-preserving Language Model Service against Embedding Inversion Attacks ACL 2025 OBLIVIATE: Robust and Practical Machine Unlearning for Large Language Models EMNLP 2025 OmniGuard: Hybrid Manipulation Localization via Augmented Versatile Deep Image Watermarking CVPR 2025