FedPurify is a framework that performs post-training data-free purification to remove malicious backdoors while preserving task-relevant knowledge in FL, and combines contrastive feature alignment with knowledge-preserving self-distillation to remove backdoor effects while preserving benign task performance.
Baolu Xue, Hanyuan Zheng, Tian-Xing Man et al.· Proceedings of the 32nd ACM...· 0 citations
Federated Learning (FL) facilitates distributed training while preserving privacy, yet remains highly vulnerable to backdoor attacks. Existing defenses primarily address these threats via robust aggregation, which reduces the influence of malicious contributions (e.g., pruning, reweighting), or through detection-based...
Baolu Xue, Hanyuan Zheng, T. Man et al.· Proceedings of the 32nd ACM...· 0 citations
This paper proposes an enhanced GraphRAG framework that integrates a transformer-based Multi-Hop Knowledge Graph Completion (KGC) model directly into the retrieval pipeline, and provides substantial gains in answer quality and reasoning capability for queries involving indirect dependencies not explicitly encoded in th...
A. Golovin, N. Zhukova, Tian-Xing Man· Machine-mediated learning· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
