Program-Level Adversarial Co-Adaptive Self-Play for Robotic Security

Summary

Coding agents can adapt robotic software by revising executable programs, but successful responses to an evolving opponent may not stay effective. The authors present a framework for program-level adversarial co-adaptive self-play, where agents generate attacks and defenses from tested opponent code and mission feedback without model fine-tuning. Two eight-generation case studies, one on autonomous driving and one on humanoid locomotion, show local task recovery but no sustained robustness.

Topics

• Robotics and embodied AI

Related items

• InfoA Layer-wise Study of How Style Rewriting Breaks the Calibration of Zero-Shot LLM Fake-News DetectorsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoEvaluating the robustness of explainable AI methods to adversarial attacks in intrusion and malware detectionSimilar attack · OpenAlex (peer-reviewed AI security)
• InfoRL-ATTACK: A Generalized Black-Box Adversarial Attack on Language Models via Reinforcement LearningSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoEvaluating Parameter-Efficient Fine-Tuning Attacks Against Non-Transferable Learning DefensesSimilar attack · Elsevier Security Journals
• InfoEscalate or Close: How Fast-Tier Models Handle Held-Out Web Attack Families in Two-Tier TriageSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)