Research map / Federated learning and privacy / Privacy attacks and secure learning
MultiKD: Backdoor Defense in Federated Graph Learning via Attention-Guided Multi-Teacher Distillation
Jiale Zhang, Yanan Wang, Bosen Rao, Chengcheng Zhu, Xiaobing Sun, Yu Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add inter-layer relation consistency to attention alignment (ablation) | MultiKD · NCI1 ASR | ASR: 25.62 -> 1.85 | Improved |
| add inter-layer relation consistency to attention alignment (ablation) | MultiKD · PROTEINS ASR | ASR: 42.62 -> 0.54 | Improved |
| add attention map alignment to relation consistency (ablation) | MultiKD · NCI1 / PROTEINS ASR | ASR: 17.70 -> 1.85 (NCI1); 14.12 -> 0.54 (PROTEINS) | Improved |
| add attention map alignment to relation consistency (ablation) | MultiKD · DD ASR | ASR: 15.26 -> 6.84 | Improved |
| add attention alignment to relation consistency on clean accuracy (ablation) | MultiKD · NCI1 ACC | ACC: 63.49 -> 62.07 | Hurt |
| server-side multi-teacher distillation purification vs FedTGE under UGBA | FGL defense · PROTEINS UGBA ASR | ASR: 72.91 -> 0.12 | Improved |
| MultiKD under non-IID splits vs FedTGE | FGL defense · NCI1 non-IID UGBA ASR | ASR: 96.45 -> 1.03 | Improved |
| over-weight attention loss relative to relation loss (high alpha, low beta) (ablation) | MultiKD · loss weights heatmap | ASR | Hurt |
| increase clean data ratio on server (ablation) | MultiKD · NCI1 | ASR / ACC | Improved |
Closest papers by meaning
- MARS: A Malignity-Aware Backdoor Defense in Federated Learning (NeurIPS 2025 · similarity 0.88)
- Infighting in the Dark: Multi-Label Backdoor Attack in Federated Learning (CVPR 2025 · similarity 0.88)
- Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective (AAAI 2024 · similarity 0.87)
- Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning (AAAI 2024 · similarity 0.87)
- Label-Free Backdoor Attacks in Vertical Federated Learning (AAAI 2025 · similarity 0.87)
- Backdoor Federated Learning by Poisoning Backdoor-Critical Layers (ICLR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
