{"data":{"id":"fabaca27-f4b4-4b9d-8251-b7cbd0f79c84","title":"Identically Trained Language Models Break on Different Jailbreaks","summary":"This study tests whether models that share pretraining data and safety post-training break on the same jailbreak prompts. Across 25 data recipes, 150 one-billion-parameter models were compared, and per-prompt non-refusal rates correlated at 0.984 between post-training seeds of one pretraining run, falling to 0.811 across pretraining seeds and 0.779 across data recipes. The best attack template on one checkpoint stayed best after a new pretraining seed in only 27% of model pairs, versus 67% after a new post-training seed. Each pretraining run was also identifiable from its non-refusal pattern across 3,211 prompts.","solution":"N/A -- no mitigation discussed in source.","labels":["research","safety"],"sourceUrl":"https://arxiv.org/abs/2610.34074v1","publishedAt":"2026-10-25T05:30:02.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"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":"2026-10-25T05:30:02.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}