{"data":{"id":"dc8c3b15-ee05-4a09-9f74-723d77bde770","title":"Byzantine-Resilient Federated Large Language Model via Hypergraph Message Passing","summary":"This paper proposes HMP-GAE, a Hypergraph Message Passing Graph Autoencoder defense that defends federated LLM training against Byzantine attacks. It represents low-rank model updates as hypergraph nodes and suppresses semantically inconsistent updates using historical checkpoints and cross-agent relational reasoning. Evaluated on Qwen-2.5 and Llama-3.2 backbones with AG News and Yahoo! Answers, it improves global accuracy by 1.21%, reduces semantic entropy by 44.08%, and lowers perplexity by 13.34% relative to existing defenses.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://arxiv.org/abs/2610.12711v1","publishedAt":"2026-10-08T20:47:08.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["other"],"issueType":"research","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":[],"affectedVendorsRaw":["Qwen-2.5","Llama-3.2"],"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":"2026-10-08T20:47:08.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity"],"aiComponentTargeted":"training_data","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"preprint","atlasIds":null}}