{"data":{"id":"be468628-fff8-4233-922f-2cc19f84c097","title":"FedPSA: Adaptive Backdoor Attacks on Federated Large Language Models via Poisoning Sensitive Prompt Layers","summary":"FedPSA is a backdoor attack framework against federated parameter-efficient fine-tuning of LLMs. It identifies the most sensitive prompt layers, poisons a minimal subset of them under parameter constraints, and uses adaptive triggers that adjust to non-IID data. Across five datasets and six language models, it reportedly outperforms the evaluated baselines while keeping clean-task performance competitive.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"http://ieeexplore.ieee.org/document/11740718","publishedAt":"2026-10-19T13:17:05.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_poisoning","supply_chain"],"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":"2026-10-19T13:17:05.000Z","capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity","safety"],"aiComponentTargeted":"model","llmSpecific":true,"classifierConfidence":0.93,"researchCategory":"peer_reviewed","atlasIds":["AML.T0010"]}}