Action-Perturbation Backdoor Attacks on Partially Observable Multiagent Systems

Summary

Researchers study backdoor attacks on reinforcement learning agents in partially observable multiagent systems. Instead of modifying a victim's observations directly, an adversary agent uses its own actions to affect what other agents observe, and a trained trigger policy, guided by auxiliary rewards, lets it activate their backdoors with few actions. Experiments show the method triggers others' backdoors efficiently, and the authors also study defenses.

Topics

• Adversarial machine learning

Related items

• MediumCVE-2026-121936: easyVoice server-side request forgery through openaiBaseUrl in /api/v1/ttsSimilar attack · NVD/CVE Database
• MediumCVE-2026-118628: MLflow get-artifacts server-side request forgery information disclosureSimilar attack · NVD/CVE Database
• HighCVE-2026-118625: MLflow Tracking Server privilege escalation via get_endpointsSimilar attack · NVD/CVE Database
• InfoWhen trust becomes the payload: Inside the threats, etc quarterly reportSimilar attack · Elastic Security Labs
• MediumCritical Langflow flaws enable authentication bypass and RCESimilar attack · CSO Online