Security & Privacy

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 PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles NAACL 2025 Partially Blinded Unlearning: Class Unlearning for Deep Networks from Bayesian Perspective AAAI 2025 PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization NAACL 2025 Personalized Label Inference Attack in Federated Transfer Learning via Contrastive Meta Learning AAAI 2025 Personalized Language Models via Privacy-Preserving Evolutionary Model Merging EMNLP 2025 PIG: Privacy Jailbreak Attack on LLMs via Gradient-based Iterative In-Context Optimization ACL 2025 PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free ACL 2025 PlugMark: A Plug-in Zero-Watermarking Framework for Diffusion Models ICCV 2025 Portcullis: A Scalable and Verifiable Privacy Gateway for Third-Party LLM Inference AAAI 2025 PoWER Never Corrupts: Tool-Agnostic Verification of Crash Consistency and Corruption Detection OSDI 2025 PPC-GPT: Federated Task-Specific Compression of Large Language Models via Pruning and Chain-of-Thought Distillation EMNLP 2025 Privacy Checklist: Privacy Violation Detection Grounding on Contextual Integrity Theory NAACL 2025 Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents EMNLP 2025 Privacy Preserving Data Selection for Bias Mitigation in Speech Models ACL 2025 Privacy-Preserving Low-Rank Adaptation Against Membership Inference Attacks for Latent Diffusion Models AAAI 2025 Privacy Preserving Solution of DCOPs by Local Search IJCAI 2025 Privacy-Preserving Speaker Verification via End-to-End Secure Representation Learning Interspeech 2025 PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration ACL 2025 Privacy, Utility and Fairness: Navigating Trade-offs in Differentially Private Machine Learning AAAI 2025 PrivateEye: In-Sensor Privacy Preservation Through Optical Feature Separation WACV 2025 Privately Counting Partially Ordered Data ICLR 2025 Private Mechanism Design via Quantile Estimation ICLR 2025 Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models ACL 2025