Privacy

Gradient Inversion Attack in Federated Learning: Exposing Text Data through Discrete Optimization COLING 2025 Gradient Inversion Attacks on Parameter-Efficient Fine-Tuning CVPR 2025 GradOT: Training-free Gradient-preserving Offsite-tuning for Large Language Models ACL 2025 GRAIN: Exact Graph Reconstruction from Gradients ICLR 2025 Graph-Embedded Structure-Aware Perceptual Hashing for Neural Network Protection and Piracy Detection CVPR 2025 Grimm: A Plug-and-Play Perturbation Rectifier for Graph Neural Networks Defending Against Poisoning Attacks AAAI 2025 Guardrails and Security for LLMs: Safe, Secure and Controllable Steering of LLM Applications ACL 2025 HARMONY: A Privacy-preserving and Sensor-agnostic Tele-monitoring system IJCAI 2025 Harnessing Global-Local Collaborative Adversarial Perturbation for Anti-Customization CVPR 2025 Hessian-Free Online Certified Unlearning ICLR 2025 Hidden in the Noise: Two-Stage Robust Watermarking for Images ICLR 2025 Hiding Images in Diffusion Models by Editing Learned Score Functions CVPR 2025 HIPP: Protecting Image Privacy via High-Quality Reversible Protected Version IJCAI 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 do we measure privacy in text? A survey of text anonymization metrics IJCNLP 2025 How Far Are We from True Unlearnability? ICLR 2025 How much of my dataset did you use? Quantitative Data Usage Inference in Machine Learning ICLR 2025 How Real Are Synthetic Therapy Conversations? Evaluating Fidelity in Prolonged Exposure Dialogues EMNLP 2025 How to Make Reproducible Research in Machine Unlearning with ERASURE IJCAI 2025 Human-Imperceptible, Machine-Recognizable Images IJCAI 2025 Human-Inspired Obfuscation for Model Unlearning: Local and Global Strategies with Hyperbolic Representations EMNLP 2025 IBAS:Imperceptible Backdoor Attacks in Split Learning with Limited Information AAAI 2025 Identify Backdoored Model in Federated Learning via Individual Unlearning WACV 2025 Identifying Unlearned Data in LLMs via Membership Inference Attacks EMNLP 2025