model utility

SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs? ACL 2025 STEREO: A Two-Stage Framework for Adversarially Robust Concept Erasing from Text-to-Image Diffusion Models CVPR 2025 Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models ICML 2025 DeRDaVa: Deletion-Robust Data Valuation for Machine Learning AAAI 2024 FairRR: Pre-Processing for Group Fairness through Randomized Response AISTATS 2024 Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor NeurIPS 2024 Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models NeurIPS 2024 Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations EMNLP 2024 Towards Safer Large Language Models through Machine Unlearning ACL 2024 WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models NeurIPS 2024 Data Poisoning Attacks Against Multimodal Encoders ICML 2023 Dropout Is NOT All You Need to Prevent Gradient Leakage AAAI 2023 Effectively Using Public Data in Privacy Preserving Machine Learning ICML 2023 Trade-Offs Between Fairness and Privacy in Language Modeling ACL 2023 DPNAS: Neural Architecture Search for Deep Learning with Differential Privacy AAAI 2022 RelaxLoss: Defending Membership Inference Attacks without Losing Utility ICLR 2022 Selective Differential Privacy for Language Modeling NAACL 2022