{"data":{"id":"96523684-9304-46ea-a0d7-67df9c7595f0","title":"SpecGuard: Detecting Multi-Turn LLM Jailbreaks via Specification-Based Runtime Monitoring","summary":"SpecGuard is a training-free framework for monitoring multi-turn LLM interactions. It maps observations into evidence-backed facts, expresses forbidden interaction patterns as Linear Temporal Logic specifications, and compiles them into symbolic finite automata that check dialogue traces at runtime or in retrospective audits. On multi-turn safety benchmarks it consistently outperforms representative open-source guard models while keeping false-positive rates controlled.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2610.36258v1","publishedAt":"2026-10-26T20:36:52.000Z","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":"2026-10-26T20:36:52.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}