Privacy

Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guarantees EMNLP 2025 LLM Unlearning via Loss Adjustment with Only Forget Data ICLR 2025 Lock on Target! Precision Unlearning via Directional Control EMNLP 2025 Masks and Mimicry: Strategic Obfuscation and Impersonation Attacks on Authorship Verification NAACL 2025 Measuring memorization in language models via probabilistic extraction NAACL 2025 Membership and Memorization in LLM Knowledge Distillation EMNLP 2025 Membership Inference Attacks with False Discovery Rate Control ICCV 2025 Memorization is Language-Sensitive: Analyzing Memorization and Inference Risks of LLMs in a Multilingual Setting ACL 2025 MEraser: An Effective Fingerprint Erasure Approach for Large Language Models ACL 2025 Mesh Watermark Removal Attack and Mitigation: A Novel Perspective of Function Space AAAI 2025 MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector AAAI 2025 Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data EMNLP 2025 Mjölnir: Breaking the Shield of Perturbation-Protected Gradients via Adaptive Diffusion AAAI 2025 MMUnlearner: Reformulating Multimodal Machine Unlearning in the Era of Multimodal Large Language Models ACL 2025 Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models ACL 2025 Model-based Large Language Model Customization as Service EMNLP 2025 Model Unlearning via Sparse Autoencoder Subspace Guided Projections EMNLP 2025 MorphMark: Flexible Adaptive Watermarking for Large Language Models ACL 2025 Mr. Snuffleupagus at SemEval-2025 Task 4: Unlearning Factual Knowledge from LLMs Using Adaptive RMU SemEval 2025 MYOPIA: Protecting Face Privacy from Malicious Personalized Text-to-Image Synthesis via Unlearnable Examples AAAI 2025 NLPART at SemEval-2025 Task 4: Forgetting is harder than Learning SemEval 2025 On the Privacy Risks of Spiking Neural Networks: A Membership Inference Analysis UAI 2025 Optimality of Matrix Mechanism on ℓ_p^p-metric ICLR 2025 Opt-Out: Investigating Entity-Level Unlearning for Large Language Models via Optimal Transport ACL 2025 Personalized Language Models via Privacy-Preserving Evolutionary Model Merging EMNLP 2025