{"data":{"id":"404edcfd-d863-45a4-9e2e-f318f244da7a","title":"Can LLMs Write Backdoors? An Empirical Security Study of Weight-Space Programming","summary":"This empirical study tests whether general-purpose LLMs can inject backdoors by directly editing target model weights from natural-language instructions, without task data, forward passes or gradients. Across an MLP on MNIST, ResNet-18 on CIFAR-10 and Qwen2.5-0.5B-Instruct on AG News, five LLMs as weight editors largely preserved clean performance while injecting backdoors, sometimes changing only six parameters in the MLP or 0.02% of the weights in the fine-tuned Qwen model. Only GPT-6 Astra succeeded on all three targets.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2611.17395v1","publishedAt":"2026-11-12T16:41:07.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"low","attackType":["other"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["GPT-6 Astra"],"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":"2026-11-12T16:41:07.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.9,"researchCategory":"preprint","atlasIds":null}}