Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918340185817088 |
|---|---|
| author | Liu, Dongrui Yu, Yi Zhang, Jie Chen, Guanxu Lin, Qihao Zhu, Hanxi Huang, Lige Zhou, Yijin Wang, Peng Shao, Shuai Zhang, Boxuan Liu, Zicheng Sun, Jingwei Li, Yu Xie, Yuejin Guo, Jiaxuan Xu, Jia Lu, Chaochao Zhou, Bowen Hu, Xia Shao, Jing |
| author_facet | Liu, Dongrui Yu, Yi Zhang, Jie Chen, Guanxu Lin, Qihao Zhu, Hanxi Huang, Lige Zhou, Yijin Wang, Peng Shao, Shuai Zhang, Boxuan Liu, Zicheng Sun, Jingwei Li, Yu Xie, Yuejin Guo, Jiaxuan Xu, Jia Lu, Chaochao Zhou, Bowen Hu, Xia Shao, Jing |
| contents | To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large Language Models (LLMs) general capabilities rapidly evolve and the proliferation of agentic AI, this version of the risk analysis technical report presents an updated and granular assessment of five critical dimensions: cyber offense, persuasion and manipulation, strategic deception, uncontrolled AI R\&D, and self-replication. Specifically, we introduce more complex scenarios for cyber offense. For persuasion and manipulation, we evaluate the risk of LLM-to-LLM persuasion on newly released LLMs. For strategic deception and scheming, we add the new experiment with respect to emergent misalignment. For uncontrolled AI R\&D, we focus on the ``mis-evolution'' of agents as they autonomously expand their memory substrates and toolsets. Besides, we also monitor and evaluate the safety performance of OpenClaw during the interaction on the Moltbook. For self-replication, we introduce a new resource-constrained scenario. More importantly, we propose and validate a series of robust mitigation strategies to address these emerging threats, providing a preliminary technical and actionable pathway for the secure deployment of frontier AI. This work reflects our current understanding of AI frontier risks and urges collective action to mitigate these challenges. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14457 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5 Liu, Dongrui Yu, Yi Zhang, Jie Chen, Guanxu Lin, Qihao Zhu, Hanxi Huang, Lige Zhou, Yijin Wang, Peng Shao, Shuai Zhang, Boxuan Liu, Zicheng Sun, Jingwei Li, Yu Xie, Yuejin Guo, Jiaxuan Xu, Jia Lu, Chaochao Zhou, Bowen Hu, Xia Shao, Jing Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Computers and Society Machine Learning To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large Language Models (LLMs) general capabilities rapidly evolve and the proliferation of agentic AI, this version of the risk analysis technical report presents an updated and granular assessment of five critical dimensions: cyber offense, persuasion and manipulation, strategic deception, uncontrolled AI R\&D, and self-replication. Specifically, we introduce more complex scenarios for cyber offense. For persuasion and manipulation, we evaluate the risk of LLM-to-LLM persuasion on newly released LLMs. For strategic deception and scheming, we add the new experiment with respect to emergent misalignment. For uncontrolled AI R\&D, we focus on the ``mis-evolution'' of agents as they autonomously expand their memory substrates and toolsets. Besides, we also monitor and evaluate the safety performance of OpenClaw during the interaction on the Moltbook. For self-replication, we introduce a new resource-constrained scenario. More importantly, we propose and validate a series of robust mitigation strategies to address these emerging threats, providing a preliminary technical and actionable pathway for the secure deployment of frontier AI. This work reflects our current understanding of AI frontier risks and urges collective action to mitigate these challenges. |
| title | Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5 |
| topic | Artificial Intelligence Computation and Language Computer Vision and Pattern Recognition Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2602.14457 |