{"data":{"id":"8319c04e-8aa9-40ac-8a96-a768ca78122f","title":"Reva: Real-Time Vulnerability Detection through Contextual Probing of Large Language Models","summary":"REVA is a real-time vulnerability detector that places a pre-computed threat model, lightweight static analysis findings and call-graph information in an LLM's context, then reads the model's internal representations with a trained probe in a single forward pass. On PrimeVul's held-out test set, REVA on GLM-5.3-Flash reaches 60.0% accuracy at about one second per function, matching the agentic detector VulTriage (59.2%) while running over 250 times faster. The probe also outperforms the LLM's own direct verdict by 14% to 17%.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.35829v1","publishedAt":"2026-10-26T17:50:09.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["GLM-5.3-Flash"],"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":"2026-10-26T17:50:09.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":null,"aiComponentTargeted":null,"llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}