{"data":{"id":"6b0f9f54-6b08-4796-bafc-06732318ebcf","title":"Jailbreak and Guard Aligned Language Models With Only Few In-Context Demonstrations","summary":"This paper shows that a few harmful in-context demonstrations can override the safety alignment of LLMs, a technique it calls the In-Context Attack (ICA). It also proposes the In-Context Defense (ICD), which uses examples of refusing harmful requests to strengthen resilience. The authors report theoretical analysis and empirical validation across multiple models, datasets and attack baselines.","solution":"In-Context Defense (ICD): bolstering model resilience with in-context examples that demonstrate refusal to produce harmful responses.","labels":["security","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11370531","publishedAt":"2026-02-02T13:17:25.000Z","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":"2026-02-02T13:17:25.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"peer_reviewed","atlasIds":["AML.T0054"]}}