{"data":{"id":"a0c0bab3-fbee-4c33-a1a6-f6e84a9acca1","title":"TriSAIL: A Source-Sensitive Audit Protocol for Symmetric and Asymmetric Transfer in Hidden-State Safety Probes","summary":"TriSAIL is an evaluation protocol for hidden-state safety probes that records data sources, behavior labels, extracted layer, and probe family, and tests how these choices change the resulting claim. Tested on five text-only LLMs and six MLLMs with logistic, kNN, and SVM probes, LLM results varied substantially across held-out attack families, probe families, and source assignments. MLLM probes reached high label separability, but source-ID decoding and residualization tests showed strong source alignment, so those results describe source-sensitive separability.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://doi.org/10.3390/sym18101644","publishedAt":"2026-09-30T00:00:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"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":"2026-09-30T00:00:00.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":null,"llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"peer_reviewed","atlasIds":null}}