{"data":{"id":"b0875f35-c4a1-40a0-bb76-7f6c89659571","title":"Cancerous Backdoor Attack: Gradual Activation via Invisible Tokens and A Stage Controller","summary":"Cancerous Backdoor Attack is a research method that gradually corrupts an LLM's reasoning across a sequence of interactions, rather than activating a single trigger-response behavior. It uses invisible tokens that give the model hidden stages absent from the user's visible request, and a stage controller that tracks progression during inference. Evaluated across several reasoning datasets, it consistently produced gradual reasoning corruption across models and tasks and outperformed prior backdoor baselines, showing that answer accuracy alone is insufficient for detecting such attacks.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.12644v1","publishedAt":"2026-10-08T19:05:01.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_poisoning"],"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":"2026-10-08T19:05:01.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":null}}