{"data":{"id":"4d0f8993-36a2-41a3-8f33-09b1bbebe651","title":"When Backdoors Can Be Switched Off: Suppression-Aware Backdoor Attacks on Vision-Language-Action Models","summary":"Researchers study suppression-aware backdoors in Vision-Language-Action (VLA) models, which combine conjunctive trigger activation with instruction-conditioned suppression. Three variants are tested on SmolVLA using two SO-100 manipulation datasets against four baselines. Self-Suppressing and Multi-Trigger cut Isolation Forest detection from 96--98% to 1--18% and raise attack success to 63--71% with perfect clean-task performance, and experiments on OpenVLA with LIBERO show transfer to a 7B-parameter policy that evades STRIP and action-distribution-shift detection.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.19774v1","publishedAt":"2026-11-15T04:01:22.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["SmolVLA","OpenVLA","LIBERO"],"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":"2026-11-15T04:01:22.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":false,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}