utility preservation

Not All Tokens Are Meant to Be Forgotten AAAI 2026 Forget the Token and Pixel: Rethinking Gradient Ascent for Concept Unlearning in Multimodal Generative Models ACL 2025 Forgetting Through Transforming: Enabling Federated Unlearning via Class-Aware Representation Transformation ICCV 2025 MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents ICML 2025 Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models ACL 2025 Privacy-and-Utility-Aware Publishing of Schedules AAAI 2025 Robust Utility-Preserving Text Anonymization Based on Large Language Models ACL 2025 Tau-Eval: A Unified Evaluation Framework for Useful and Private Text Anonymization EMNLP 2025 Disguise without Disruption: Utility-Preserving Face De-identification AAAI 2024 FLIP: A Utility Preserving Privacy Mechanism for Time Series JMLR 2023 Privacy- and Utility-Preserving NLP with Anonymized data: A case study of Pseudonymization ACL 2023 How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection ICML 2022 Utility Preservation of Clinical Text After De-Identification ACL 2022 Avoiding Side Effects in Complex Environments NeurIPS 2020 Deep Reinforcement Learning-based Text Anonymization against Private-Attribute Inference EMNLP 2019 How to Build User Simulators to Train RL-based Dialog Systems EMNLP 2019