Privacy

Targeted Forgetting of Image Subgroups in CLIP Models CVPR 2025 Task-Agnostic Language Model Watermarking via High Entropy Passthrough Layers AAAI 2025 Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization EMNLP 2025 TDDBench: A Benchmark for Training data detection ICLR 2025 Temporal Unlearnable Examples: Preventing Personal Video Data from Unauthorized Exploitation by Object Tracking ICCV 2025 Tensor-aggregated LoRA in Federated Fine-tuning ICCV 2025 Test-Time Backdoor Detection for Object Detection Models CVPR 2025 The Mainstays of Trustworthy Machine Learning AAAI 2025 Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems CVPR 2025 The Pitfalls of “Security by Obscurity” and What They Mean for Transparent AI AAAI 2025 The Tug of War Within: Mitigating the Fairness-Privacy Conflicts in Large Language Models ACL 2025 Thunder-DeID: Accurate and Efficient De-identification Framework for Korean Court Judgments EMNLP 2025 Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model ICLR 2025 Tokens for Learning, Tokens for Unlearning: Mitigating Membership Inference Attacks in Large Language Models via Dual-Purpose Training ACL 2025 Toward Efficient Data-Free Unlearning AAAI 2025 Toward Robust Non-Transferable Learning: A Survey and Benchmark IJCAI 2025 Towards All-in-One Medical Image Re-Identification CVPR 2025 Towards Federated RLHF with Aggregated Client Preference for LLMs ICLR 2025 Towards hyperparameter-free optimization with differential privacy ICLR 2025 Towards Operationalizing Right to Data Protection NAACL 2025 Towards Privacy-Preserving Split Learning for ControlNet WACV 2025 Towards Reverse Engineering of Language Models: A Survey EMNLP 2025 Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning ICLR 2025 Towards Source-Free Machine Unlearning CVPR 2025 Tracing Training Footprints: A Calibration Approach for Membership Inference Attacks Against Multimodal Large Language Models EMNLP 2025