{"data":{"id":"72157c36-ddce-4a57-bf98-3f82a4b9f106","title":"Decision Models as Retrieval Gates Against Injection and Pollution","summary":"The authors test whether open-weight decision models can screen retrieved web passages for hidden injected instructions and synthetic misleading pages. On a 1,000-question benchmark, a Kev-4B gate reading each passage's HTML cut attack success from 27.9% with no defence to 13.6% with published mitigations and to 5.7% with the gate added, at 76 ms per passage and 4 of 186 benign pages wrongly flagged. On a 200-query pollution testbed, filtering the candidate pool before selecting the top ten kept fake pages out of answers (0.5% exposure) and held accuracy at 83%, against 28% with no filter.","solution":"Gate retrieved passages with a released open-weight decision model such as Kev-4B that reads each passage's HTML, applied to the candidate pool before the top ten are chosen; the published mitigations of sanitisation, normalisation and citation prompting are also tested as baselines.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.08325v1","publishedAt":"2026-11-05T17:19:19.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["prompt_injection","rag_poisoning"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Kev-4B"],"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":"2026-11-05T17:19:19.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","safety"],"aiComponentTargeted":"rag","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0051","AML.T0070"]}}