{"data":{"id":"12692972-d4c4-489f-9777-db22458342be","title":"DETER: Suppression During Pretraining for Tamper Resistance","summary":"Researchers ask whether suppressing knowledge during pretraining makes unwanted capabilities in open-weight language models harder to recover through fine-tuning. Gradient ascent interleaved with pretraining on a filtered corpus raised the fine-tuning cost of medical knowledge: at 1B parameters, matching the held-out PubMed loss of an unfiltered model required over 20 times as many PubMed fine-tuning tokens as filtering alone. The authors report a favorable trade-off between fine-tuning difficulty and held-out loss on retained data, and release code at github.com/MEGlr/DETER.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2611.15479v1","publishedAt":"2026-11-11T13:43:32.000Z","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":"2026-11-11T13:43:32.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}