1
How to Steal an AI Model’s Private Thoughts
破解加密推理闭环，看研究团队如何窥探AI私有思考，安全边界再受拷问
In August 2026, a team at MATS Research, the ELLIS Institute Tübingen, and the Max Planck Institute for Intelligent Systems wanted to test whethe…
2
Stress Testing Unlearning Algorithms
系统检验机器遗忘算法在极端压力下的鲁棒性，为隐私保护研究划出新基准。
arXiv:2608.22527v1 Announce Type: new Abstract: Recently, machine unlearning, the removal of specific training data influence from a model, has gained…
3
SAUL: Sharpness-Aware Augmented-Lagrangian Unlearning
SAUL把锐度感知与增强拉格朗日结合，给机器遗忘难题开了一剂新药方。
arXiv:2608.16249v1 Announce Type: new Abstract: Machine unlearning in Large Language Models (LLMs) faces a critical trade-off between erasing target k…
4
AlienLM: Alienization of Language for API-Boundary Privacy in Black-Box LLMs
用语言「陌生化」技术为大模型API边界隐私保驾护航，黑盒场景下实现隐私保护新思路
arXiv:2601.22710v2 Announce Type: replace-cross Abstract: Modern LLMs are increasingly accessed via black-box APIs, requiring users to transmit sensit…
5
Natural Identifiers for Privacy and Data Audits in Large Language Models
用自然标识符给大模型做隐私审计，全新视角兼顾数据保护与可追溯性，AI安全领域值得关注的前沿研究。
arXiv:2606.24408v1 Announce Type: new Abstract: Assessing the privacy of large language models (LLMs) presents significant challenges. In particular, …