{"data":{"id":"87660e9f-1bd7-4088-8b84-8c0480964abe","title":"Detecting Chain-of-Thought Hijacking in Backdoored Multimodal Large Reasoning Models","summary":"Researchers study chain-of-thought hijacking in multimodal large reasoning models (MLRMs), where a visual trigger from a poisoned fine-tuning backdoor redirects a reasoning chain to an attacker-chosen answer. They formalize belief inertia, the cumulative next-token entropy of a reasoning span minus the answer-belief revision it induces, and restrict it to image-dependent spans to get visual belief inertia (VBI). Their training-free detector, InertiaGuard, flags traces whose VBI falls below a threshold calibrated on clean traces, and it reportedly outperforms baselines across attacks and benchmarks.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.16598v1","publishedAt":"2026-10-12T11:18:32.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"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":"2026-10-12T11:18:32.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}