Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.06786 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915484317777920 |
|---|---|
| author | Sun, Youbang Wang, Xiang Fu, Jie Lu, Chaochao Zhou, Bowen |
| author_facet | Sun, Youbang Wang, Xiang Fu, Jie Lu, Chaochao Zhou, Bowen |
| contents | In this position paper, we address the persistent gap between rapidly growing AI capabilities and lagging safety progress. Existing paradigms divide into ``Make AI Safe'', which applies post-hoc alignment and guardrails but remains brittle and reactive, and ``Make Safe AI'', which emphasizes intrinsic safety but struggles to address unforeseen risks in open-ended environments. We therefore propose \textit{safe-by-coevolution} as a new formulation of the ``Make Safe AI'' paradigm, inspired by biological immunity, in which safety becomes a dynamic, adversarial, and ongoing learning process. To operationalize this vision, we introduce \texttt{R$^2$AI} -- \textit{Resistant and Resilient AI} -- as a practical framework that unites resistance against known threats with resilience to unforeseen risks. \texttt{R$^2$AI} integrates \textit{fast and slow safe models}, adversarial simulation and verification through a \textit{safety wind tunnel}, and continual feedback loops that guide safety and capability to coevolve. We argue that this framework offers a scalable and proactive path to maintain continual safety in dynamic environments, addressing both near-term vulnerabilities and long-term existential risks as AI advances toward AGI and ASI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06786 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | \texttt{R$^\textbf{2}$AI}: Towards Resistant and Resilient AI in an Evolving World Sun, Youbang Wang, Xiang Fu, Jie Lu, Chaochao Zhou, Bowen Machine Learning In this position paper, we address the persistent gap between rapidly growing AI capabilities and lagging safety progress. Existing paradigms divide into ``Make AI Safe'', which applies post-hoc alignment and guardrails but remains brittle and reactive, and ``Make Safe AI'', which emphasizes intrinsic safety but struggles to address unforeseen risks in open-ended environments. We therefore propose \textit{safe-by-coevolution} as a new formulation of the ``Make Safe AI'' paradigm, inspired by biological immunity, in which safety becomes a dynamic, adversarial, and ongoing learning process. To operationalize this vision, we introduce \texttt{R$^2$AI} -- \textit{Resistant and Resilient AI} -- as a practical framework that unites resistance against known threats with resilience to unforeseen risks. \texttt{R$^2$AI} integrates \textit{fast and slow safe models}, adversarial simulation and verification through a \textit{safety wind tunnel}, and continual feedback loops that guide safety and capability to coevolve. We argue that this framework offers a scalable and proactive path to maintain continual safety in dynamic environments, addressing both near-term vulnerabilities and long-term existential risks as AI advances toward AGI and ASI. |
| title | \texttt{R$^\textbf{2}$AI}: Towards Resistant and Resilient AI in an Evolving World |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.06786 |