{"data":{"id":"a5fd7ddd-9dc0-4efc-abc5-fe5a3f89ea59","title":"Addition by Subtraction: Toward Mitigating Fragile Safety Alignment in Large Language Models","summary":"Researchers study how safety alignment in large language models depends on a small set of safety-critical neurons and a single refusal direction, so pruning or ablating them can undermine aligned behavior. They propose Addition by Subtraction, which gradually removes identified safety-critical neurons during finetuning and uses preference optimization to restore safe behavior through other model components. Across four models from three vendors, the resulting models resist pruning-based and black-box jailbreak attacks better, with attack success rates reduced by up to 90% for some attacks.","solution":"Addition by Subtraction: gradually remove identified safety-critical neurons during finetuning and use preference optimization to re-establish safety-aligned behavior through other parts of the model.","labels":["security","research","safety"],"sourceUrl":"https://arxiv.org/abs/2611.06553v1","publishedAt":"2026-11-04T14:18:05.000Z","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":"2026-11-04T14:18:05.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["safety","integrity"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":"preprint","atlasIds":["AML.T0054"]}}