Privacy

Learning Together Securely: Prototype-Based Federated Multi-Modal Hashing for Safe and Efficient Multi-Modal Retrieval AAAI 2025 Learning to Refuse: Towards Mitigating Privacy Risks in LLMs COLING 2025 Learning to Rewind via Iterative Prediction of Past Weights for Practical Unlearning AAAI 2025 Less Static, More Private: Towards Transferable Privacy-Preserving Action Recognition by Generative Decoupled Learning ICCV 2025 Leveraging Semantic Triples for Private Document Generation with Local Differential Privacy Guarantees EMNLP 2025 LiteLMGuard: Seamless and Lightweight On-Device Guardrails for Small Language Models against Quantization Vulnerabilities IJCNLP 2025 Little Is Enough: Boosting Privacy by Sharing Only Hard Labels in Federated Semi-Supervised Learning AAAI 2025 LLM Evaluate: An Industry-Focused Evaluation Tool for Large Language Models COLING 2025 LLM-Generated Passphrases That Are Secure and Easy to Remember NAACL 2025 LLMs are Privacy Erasable EMNLP 2025 LMEraser: Large Model Unlearning via Adaptive Prompt Tuning AISTATS 2025 LNE-Blocking: An Efficient Framework for Contamination Mitigation Evaluation on Large Language Models EMNLP 2025 Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank Adaptation CVPR 2025 Locally Private Causal Inference for Randomized Experiments JMLR 2025 Locally Private Sampling with Public Data AISTATS 2025 LoRA Unlearns More and Retains More (Student Abstract) AAAI 2025 LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty CVPR 2025 Low-Entropy Watermark Detection via Bayes’ Rule Derived Detector ACL 2025 Low-Rank Adaptation in Multilinear Operator Networks for Security-Preserving Incremental Learning CVPR 2025 LUME: LLM Unlearning with Multitask Evaluations EMNLP 2025 Machine Unlearning Fails to Remove Data Poisoning Attacks ICLR 2025 Machine Unlearning of Personally Identifiable Information in Large Language Models EMNLP 2025 Machine Unlearning via Simulated Oracle Matching ICLR 2025 MALTO at SemEval-2025 Task 4: Dual Teachers for Unlearning Sensitive Content in LLMs SemEval 2025 Measuring memorization in RLHF for code completion ICLR 2025