1
PVF:Understanding AI Vulnerability Against SDCs
揭示AI模型在静默数据损坏下的脆弱性，为可靠性部署提供关键参考。
arXiv:2405.01741v4 Announce Type: replace-cross Abstract: Reliability of AI systems is a fundamental concern for the successful deployment and widespr…
2
The Autonomy Tax: Defense Training Breaks LLM Agents
论文揭示防御训练会让LLM智能体付出“自主性税”，性能与安全如何平衡？
arXiv:2603.19423v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API …
3
Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs
揭示LLM水印在多重模型访问下的致命缺陷：独立扰动轻松被线性集成抹除，对AI安全与版权保护提出新挑战。
arXiv:2605.30501v1 Announce Type: new Abstract: Watermarking embeds statistical signatures in AI-generated text for detection and attribution. We reve…
4
On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs
首份系统研究RL微调VLM的鲁棒性与思维链一致性，揭示模型脆弱性根源
arXiv:2602.12506v3 Announce Type: replace Abstract: Reinforcement learning (RL) finetuning has become a key technique for enhancing large language mod…