{"data":{"id":"4642ae78-30a1-49f0-b6a8-d378aaa80145","title":"TMT: Runtime Backdoor Detection for Vision-Language-Action Policies on Unseen Tasks","summary":"TMT is a runtime backdoor detector for vision-language-action (VLA) policies, built on token manifold and latent transition modeling and trained on benign rollouts. The authors also explore policy purification through self-distillation, using a frozen copy of the backdoored policy as a teacher. In a post-hoc comparison with ten baselines, TMT achieves state-of-the-art detection on unseen tasks across three VLA backdoor attacks.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.09462v1","publishedAt":"2026-10-07T05:20:16.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["other"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-10-07T05:20:16.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":null}}