{"data":{"id":"e6b3c167-8e71-4220-8f6b-9246a3a0a454","title":"GuardrailAgent: An Agentic Framework for Jailbreak Defense","summary":"GuardrailAgent is a multi-agent defense framework against jailbreak attacks on LLMs. It autonomously builds a continuously updated knowledge base of attack characteristics that supports input- and output-side detection, and a feedback module folds misclassified cases back in. Tested on over ten representative jailbreaks, it reached a 93.1% input-side detection rate, 93.9% overall detection, and a 95.8% F1 score while adapting to unseen attacks.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2611.09734v1","publishedAt":"2026-11-06T17:09:55.000Z","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":"2026-11-06T17:09:55.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}