{"data":{"id":"1a266a7e-10eb-49c7-b5ce-c56d824f5486","title":"TERM: Target-Free Jailbreak Defense via Entropy-Guided Residual Modulation","summary":"This paper proposes Target-free Entropy-guided Residual Modulation (TERM), an inference-time defense against jailbreak attacks on LLMs. TERM calibrates attention entropy against each prompt's own prefill baseline and uses the result to bound-scale the model's own residual updates, without a predefined safety direction. The authors report improved jailbreak robustness with low over-refusal across Llama, Qwen, and Gemma models from 0.6B to 32B parameters, with modest inference overhead.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.13577v1","publishedAt":"2026-11-10T04:52:10.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Llama","Qwen","Gemma","Qwen3"],"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":"2026-11-10T04:52:10.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}