{"data":{"id":"a3158b8d-98b7-4df2-a67b-a9d1f250174a","title":"Online Safety Analysis for LLMs: A Benchmark, an Assessment, and a Path Forward","summary":"This paper evaluates existing online safety analysis methods, which detect unsafe LLM outputs during generation rather than after it. The authors run a pilot study showing unsafe outputs can be detected early, then release the first public benchmark covering multiple methods, models, tasks, datasets and metrics. They also test hybrid methods that combine several detectors into one safety conclusion.","solution":"N/A -- no mitigation discussed in source.","labels":["safety","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11145129","publishedAt":"2025-08-29T13:19:06.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["LLMs"],"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":"2025-08-29T13:19:06.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"peer_reviewed","atlasIds":null}}