{"data":{"id":"8ed65556-ff67-4e80-8b65-b2dfaa8ac40b","title":"StableJudge: A Lightweight Adversarial Defense Framework for LLM-as-a-Judge","summary":"Researchers propose StableJudge, a lightweight defense for LLM-as-a-Judge pipelines against score-hijacking prompt injection embedded in evaluated content. A compact 0.13B Sentry localizes injected spans and sanitizes them before scoring, trained on adversarially evolving attacks, and deterministic fine-grained scores are derived from the judge's output distribution. On held-out scientific abstracts and out-of-distribution attack variants, it improves score recovery under attack while largely preserving general performance.","solution":"StableJudge is itself the proposed mitigation: a reusable pre-scoring 0.13B Sentry that localizes injected spans and performs targeted sanitization before evaluation, with the judge model left unchanged. Code and data will be released.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.16814v1","publishedAt":"2026-10-12T14:00:13.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection"],"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":"2026-10-12T14:00:13.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity"],"aiComponentTargeted":"api","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0051"]}}