Privacy

FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning CVPR 2025 Fingerprinting Denoising Diffusion Probabilistic Models CVPR 2025 First Steps Towards Voice Anonymization for Code-Switching Speech Interspeech 2025 From Allies to Adversaries: Manipulating LLM Tool-Calling through Adversarial Injection NAACL 2025 From Teacher to Student: Tracking Memorization Through Model Distillation ACL 2025 Gamma-Guard: Lightweight Residual Adapters for Robust Guardrails in Large Language Models EMNLP 2025 Gaussian Differentially Private Human Faces Under a Face Radial Curve Representation ICLR 2025 Geminio: Language-Guided Gradient Inversion Attacks in Federated Learning ICCV 2025 General Staircase Mechanisms for Optimal Differential Privacy AISTATS 2025 Gibberish is All You Need for Membership Inference Detection in Contrastive Language-Audio Pretraining NAACL 2025 Guardrails and Security for LLMs: Safe, Secure and Controllable Steering of LLM Applications ACL 2025 HoneypotNet: Backdoor Attacks Against Model Extraction AAAI 2025 Howard University-AI4PC at SemEval-2025 Task 4: Unlearning Sensitive Content From Large Language Models Using Finetuning and Distillation for Selective Knowledge Removal SemEval 2025 How Private are Language Models in Abstractive Summarization? EMNLP 2025 Identifying Unlearned Data in LLMs via Membership Inference Attacks EMNLP 2025 IDFace: Face Template Protection for Efficient and Secure Identification ICCV 2025 I Know You Did Not Write That! A Sampling Based Watermarking Method for Identifying Machine Generated Text COLING 2025 IncogniText: Privacy-enhancing Conditional Text Anonymization via LLM-based Private Attribute Randomization IJCNLP 2025 Investigating How Pre-training Data Leakage Affects Models’ Reproduction and Detection Capabilities EMNLP 2025 Investigating User Perspectives on Differentially Private Text Privatization NAACL 2025 iShumei-Chinchunmei at SemEval-2025 Task 4: A balanced forgetting and retention multi-task framework using effective unlearning loss SemEval 2025 Is Merging Worth It? Securely Evaluating the Information Gain for Causal Dataset Acquisition AISTATS 2025 Jailbreaking the Non-Transferable Barrier via Test-Time Data Disguising CVPR 2025 Keep Security! Benchmarking Security Policy Preservation in Large Language Model Contexts Against Indirect Attacks in Question Answering EMNLP 2025 Leaky Thoughts: Large Reasoning Models Are Not Private Thinkers EMNLP 2025