{"data":{"id":"1b73def6-3a2d-4223-9525-0b7202efd3a8","title":"VRMaaS: Verifiable Reward-Model-as-a-Service for Trustworthy LLM Alignment","summary":"Researchers propose VRMaaS, a framework that makes each reward model score returned by a service a proof-carrying artifact, binding request identity, committed weights, verifier and configuration identifiers, and the package digest so auditors can check it without rerunning the private model. A GPU prototype on 1B, 3B, and 8B reward models keeps 93.5-99% pairwise agreement with the baseline and rejects every tested service-field substitution, generating complete artifacts in 49.8-206.1 seconds and verifying them in 1.94-5.11 seconds.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.14984v1","publishedAt":"2026-11-11T03:41:30.000Z","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":"2026-11-11T03:41:30.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity"],"aiComponentTargeted":"api","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}