{"data":{"id":"a9ef1f90-9901-4714-814e-ccb57c58a1e0","title":"TraceRouter++: Causal Semantic Routing Realignment via Optimal Transport","summary":"TraceRouter++ is a safety intervention framework for large foundation models that traces causal routing pathways activated by harmful inputs and realigns their unsafe activations. It locates a sensitive onset layer via attention divergence, maps sparse autoencoder features to downstream circuits through feature influence scores, and applies a constrained optimal transport soft realignment. The authors report improved adversarial robustness across LLMs, MLLMs and diffusion models with a favorable safety-utility trade-off over evaluated baselines.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2611.04878v2","publishedAt":"2026-11-03T13:30:34.000Z","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":"2026-11-03T13:30:34.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}