{"data":{"id":"82788816-881e-49fc-a750-91f130ea1048","title":"SemAlign-PFL:Exploring stealthy and persistent backdoor attacks against personalized federated learning","summary":"Researchers discovered a new type of backdoor attack (hidden malicious code inserted into AI systems) that works against personalized federated learning (a privacy-focused method where multiple computers train an AI model together without sharing raw data). The attack is designed to be stealthy and persistent, meaning it can hide from detection and remain in the system over time.","solution":"N/A -- no mitigation discussed in source.","labels":["security","research"],"sourceUrl":"https://www.sciencedirect.com/science/article/pii/S2214212626001675?dgcid=rss_sd_all","publishedAt":"2026-06-06T18:00:59.364Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":["model_poisoning"],"issueType":"research","affectedPackages":null,"affectedVendors":[],"affectedVendorsRaw":[],"classifierModel":"claude-haiku-4-5-20251001","classifierPromptVersion":"v3","cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"patchAvailable":null,"disclosureDate":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"advanced","impactType":["integrity"],"aiComponentTargeted":"training_data","llmSpecific":false,"classifierConfidence":0.88,"researchCategory":"peer_reviewed","atlasIds":null}}