{"data":{"id":"5fb15665-6895-43f4-9c77-cb3ad9755597","title":"POEM: Output-Relative Block-Sparse Attention for Long-Context Prefilling","summary":"The 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 adaptive scaling to bound changes to the model's residual updates, without a predefined safety direction. Tested against seven defenses, seven jailbreak attacks and two over-refusal benchmarks on Llama, Qwen and Gemma models (Qwen3 from 0.6B to 32B), it improves jailbreak robustness with low over-refusal and modest inference overhead.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2611.13578v1","publishedAt":"2026-11-10T04:52:58.000Z","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"],"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":"2026-11-10T04:52:58.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}