{"data":{"id":"9f35ec3c-bb8f-4554-ade1-e13ed7545fc2","title":"CompanionSafe: From Multi-turn Safety Evaluation to Guardrails for AI Companions","summary":"CompanionSafe is a framework for evaluating and mitigating safety risks in AI companions, which provide ongoing emotional support through sustained relational interaction. Its evaluation component, CompanionEval, builds 1,300 relationally grounded multi-turn settings across four turn tiers from diverse personas, matched companion characters, and dialogue scenarios. Its mitigation component, CompanionGuard, turns benchmark-exposed failures into turn-localized supervision for companion-specific risk detection. The authors report that even strong LLMs and existing guard models remain vulnerable to companion-specific relational harms, and that safety risks increase as interactions grow longer.","solution":"N/A -- no mitigation discussed in source.","labels":["safety","research"],"sourceUrl":"https://arxiv.org/abs/2610.18095v1","publishedAt":"2026-10-13T10:13:07.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["LLM-based AI companions","existing guard models"],"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":"2026-10-13T10:13:07.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":null}}