{"data":{"id":"f70bf680-0cd1-4781-a9b3-19b43b126636","title":"Safety Mid-Training: Internalizing LLM Safety as a Foundational Capability","summary":"Researchers propose safety mid-training, a stage between pre-training and post-training that jointly develops safety and general reasoning by treating safety as a learnable capability shared with general tasks. The base model generates structured documents and reasoning traces from safety and utility prompts for this stage. Relative to Qwen3-1.7B, 4B, and 8B base models, it reduces average attack success rate (ASR) by 72% to 81% while improving general capability, and the safety gains persist through subsequent SFT and GRPO.","solution":"N/A -- no mitigation discussed in source.","labels":["safety","research"],"sourceUrl":"https://arxiv.org/abs/2610.26809v1","publishedAt":"2026-10-19T17:49:49.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["jailbreak"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Qwen3-1.7B","Qwen3-4B","Qwen3-8B"],"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":"2026-10-19T17:49:49.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}