Research map / Federated learning and privacy / Privacy attacks and secure learning
Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learning
Wenjin Mo, Zhiyuan Li, Minghong Fang, Mingwei Fang
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 greedy mask sample selection instead of random selection (ablation) | FedPoisonMIA · Texas100 | attack accuracy: 0.757 -> 0.894 (DP, Non-IID); improvement of over 20% | Improved |
| add greedy mask sample selection instead of random selection (ablation) | FedPoisonMIA · Texas100 (Trimmed-mean, Non-IID) | attack accuracy: 0.748 -> 0.890 | Improved |
| use FedPoisonMIA instead of best baseline attack | FedPoisonMIA · Texas100 (Median, Non-IID) | attack accuracy: 0.770 -> 0.930 | Improved |
| use FedPoisonMIA instead of best baseline attack | FedPoisonMIA · Texas100 (ATM, Non-IID) | attack accuracy: 0.773 -> 0.853 | Improved |
| defend with ATM instead of FedAvg | ATM · Texas100 Non-IID (FedPoisonMIA) | attack accuracy: 0.897 -> 0.853 | Improved |
| defend with ATM instead of Median | ATM · Texas100 Non-IID (FedPoisonMIA) | attack accuracy: 0.930 -> 0.853 | Improved |
| defend with ATM instead of FedAvg | ATM · CIFAR-10 Non-IID (FedPoisonMIA) | attack accuracy: 0.786 -> 0.650 | Improved |
| defend with ATM instead of Median | ATM · FER2013 IID (FedPoisonMIA) | attack accuracy: 0.816 -> 0.786 | Hurt |
| use partial-knowledge instead of full-knowledge attack | FedPoisonMIA · all datasets | attack accuracy: maximum degradation of 8.0% | No clear effect |
| increase fraction of malicious clients from 10% to 30% (ablation) | FedPoisonMIA · Texas100 | attack accuracy: nearly 100% at 30% malicious versus baselines around 90% | Improved |
| increase the total number of clients (ablation) | FedPoisonMIA · Texas100 | attack accuracy: 8 to 30 clients, accuracy decreases overall | Hurt |
| increase the number of attack samples from 100 to 500 (ablation) | FedPoisonMIA · Texas100 | attack accuracy: 100 to 500 samples, accuracy gradually decreases | Hurt |
Closest papers by meaning
- FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning (CVPR 2025 · similarity 0.90)
- Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning (NeurIPS 2025 · similarity 0.90)
- Model Poisoning Attacks to Federated Learning via Multi-Round Consistency (CVPR 2025 · similarity 0.89)
- FedREDefense: Defending against Model Poisoning Attacks for Federated Learning using Model Update Reconstruction Error (ICML 2024 · similarity 0.89)
- Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning (NeurIPS 2024 · similarity 0.89)
- Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning (NeurIPS 2026 · similarity 0.88)
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.
