Event
Program-Level Self-Play Framework for Robot Safety
1 reports · 1 sources
Leo Benaharon and co-authors propose a program-level adversarial co-adaptive self-play framework: coding agents generate attacks and defenses based on tested opponent code and task feedback, without model fine-tuning. The framework provides an external program interface for autonomous driving and an SDK-level defense interface for humanoid robot locomotion. Two sets of eight-generation case studies show that the driving defender introduced direct drive recovery, and the humanoid defender modified input state validation; the authors state that these responses only brought local task recovery and did not establish sustained robustness.
Report timeline
- Program-Level Adversarial Co-Adaptive Self-Play for Robot Security
The paper proposes a program-level adversarial co-adaptive self-play framework that lets coding agents generate attacks and defenses based on opponent code and task feedback, without model fine-tuning. The framework provides external program interfaces for autonomous driving and SDK-level defense interfaces for humanoid robot locomotion; two eight-generation case studies show that the driving defender introduced direct-actuation recovery, while the humanoid defender revised incoming-state validation. These responses provided only local task recovery and did not establish sustained robustness.
arXiv cs.RO ·