{"data":{"id":"1a8e59d1-f2a2-44f5-86b7-e29e08769a81","title":"Hijacking a Trusted LLM in Real-World Quantized Deployments Only Requires a Disguised Adapter","summary":"Researchers present QHijack-LoRA, an adapter-only attack that passes audit under full-precision conditions but hijacks decisions such as content moderation and function selection once the same base model is quantized for deployment. The attack needs no changes to the trusted base model or knowledge of the victim's quantization configuration. The authors also propose a cross-precision paired audit that checks the adapter in its intended deployment configuration.","solution":"The authors propose a cross-precision paired audit that checks the candidate adapter in its intended deployment configuration.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.14978v1","publishedAt":"2026-11-11T03:37:09.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["supply_chain","model_poisoning"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["LoRA adapters","quantized LLM deployments"],"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":"2026-11-11T03:37:09.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":["AML.T0010"]}}