Research map / Federated learning and privacy / Privacy attacks and secure learning
A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning
Hangfan Zhang, Jinyuan Jia, Jinghui Chen, Lu Lin, Dinghao Wu
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 adversarial adaptation loss (ablation) | A3FL · CIFAR-10 FedAvg P=20, 1000 rounds after attack | ASR (%): 69.01 -> 84.65 | Improved |
| add adversarial adaptation loss (ablation) | A3FL · CIFAR-10 FedAvg P=20, 500 rounds after attack | ASR (%): 93.35 -> 97.66 | Improved |
| add adversarial adaptation loss (ablation) | A3FL · CIFAR-10 FedAvg P=20, at attack end | ASR (%): 100.0 -> 100.0 | No clear effect |
| vary trigger size from 3x3 to 10x10 (ablation) | A3FL · CIFAR-10 Norm Clipping | ASR (%): best-worst gap 1.75% | No clear effect |
| vary lambda0 over 0 to 1 (ablation) | A3FL · CIFAR-10 Norm Clipping | ASR (%): gap 0.5% | No clear effect |
| use A3FL instead of baseline attacks | backdoor attack on FL · CIFAR-10 Norm Clipping, 1 compromised client | ASR (%): 13.9 -> 99.75 | Improved |
| attack with A3FL vs no attack | global model utility · CIFAR-10 across defenses | clean accuracy (%): max drop 0.28% | No clear effect |
Closest papers by meaning
- Bad-PFL: Exploiting Backdoor Attacks against Personalized Federated Learning (ICLR 2025 · similarity 0.90)
- Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning (AAAI 2024 · similarity 0.88)
- Resisting Backdoor Attacks in Federated Learning via Bidirectional Elections and Individual Perspective (AAAI 2024 · similarity 0.88)
- SADBA: Self-Adaptive Distributed Backdoor Attack Against Federated Learning (AAAI 2025 · similarity 0.88)
- Backdoor Federated Learning by Poisoning Backdoor-Critical Layers (ICLR 2024 · similarity 0.88)
- Infighting in the Dark: Multi-Label Backdoor Attack in Federated Learning (CVPR 2025 · 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.
