1
Auditing of Unlearning Algorithms
聚焦机器学习遗忘算法的可信度审计，探讨如何验证模型真正删除用户数据，关乎隐私合规与AI治理。
arXiv:2607.05898v1 Announce Type: new Abstract: Evaluating whether unlearning algorithms truly remove training data influence remains an open challeng…
2
Fair Cognitive Impairment Detection Through Unlearning
用「去学习」技术消除模型偏见，实现公平的认知障碍检测，AI医疗伦理前沿探索。
arXiv:2606.18571v1 Announce Type: new Abstract: Mild Cognitive Impairment (MCI) is a medical condition characterized by a noticeable decline in memory…
3
Natively Unlearnable Large Language Models
提出原生不可遗忘的LLM设计，通过解耦参数解决训练数据来源纠缠难题，为模型安全提供新思路。
arXiv:2606.13873v1 Announce Type: new Abstract: Unlearning aims to remove the influence of specific training data sources, but this has proved challen…
4
Backdoor Unlearning Generalization: A Path Toward the Removal of Unknown Triggers in LLMs
提出后门遗忘泛化新路径，让大模型摆脱未知触发器威胁，捍卫LLM安全防线。
arXiv:2606.03785v1 Announce Type: new Abstract: Backdoor attacks in Large Language Models (LLMs) are a growing security concern, where models can gene…
5
Unlearning Isn't Invisible: Detecting Unlearning Traces in LLMs from Model Outputs
遗忘并非不可见：本文提出从LLM输出中检测“遗忘学习”迹象的新方法，为模型安全与隐私审计提供重要技术路径。
arXiv:2506.14003v5 Announce Type: replace Abstract: Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, …