mlsanityData to 14 Oct 2026

FLAIRS: FPGA-Accelerated Inference-Resistant & Secure Federated Learning

arXiv 2308.00553 ↗First posted 1 Aug 2023cs.CRcited by 3

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

Federated Learning (FL) has become very popular since it enables clients to train a joint model collaboratively without sharing their private data. However, FL has been shown to be susceptible to backdoor and inference attacks. While in the former, the adversary injects manipulated updates into the aggregation process; the latter leverages clients' local models to deduce their private data. Contemporary solutions to address the security concerns of FL are either impractical for real-world deployment due to high-performance overheads or are tailored towards addressing specific threats, for instance, privacy-preserving aggregation or backdoor defenses. Given these limitations, our research delves into the advantages of harnessing the FPGA-based computing paradigm to overcome performance bottlenecks of software-only solutions while mitigating backdoor and inference attacks. We utilize FPGA-based enclaves to address inference attacks during the aggregation process of FL. We adopt an advanced backdoor-aware aggregation algorithm on the FPGA to counter backdoor attacks. We implemented and evaluated our method on Xilinx VMK-180, yielding a significant speed-up of around 300 times on the IoT-Traffic dataset and more than 506 times on the CIFAR-10 dataset.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 12 of its 47 references that are in the map. First posted on arXiv 1 Aug 2023.

Builds on

12 of 47 references.

References · 12

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  3. 2018How To Backdoor Federated Learningcited by 765
  4. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  5. 2019Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learningcited by 122
  6. 2022DeepSight: Mitigating Backdoor Attacks in Federated Learning Through Deep Model Inspectioncited by 81
  7. 2020BaFFLe: Backdoor detection via Feedback-based Federated Learningcited by 53
  8. 2022FL-Defender: Combating Targeted Attacks in Federated Learningcited by 15
  9. 2021Byzantine-Robust and Privacy-Preserving Framework for FedMLcited by 14
  10. 2020FPGA-Based Hardware Accelerator of Homomorphic Encryption for Efficient Federated Learningcited by 6
  11. 2021ShEF: Shielded Enclaves for Cloud FPGAscited by 5
  12. 2022FLVoogd: Robust And Privacy Preserving Federated Learningcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 0; 2025: 1.

3 papers.

  1. 2023FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learningcited by 27
  2. 2025SafeSplit: A Novel Defense Against Client-Side Backdoor Attacks in Split Learning (Full Version)cited by 7
  3. 2023FLEDGE: Ledger-based Federated Learning Resilient to Inference and Backdoor Attackscited by 4

Similar, not cited

Close in wording, no citation either way

  1. 2025FL-PLAS: Federated Learning with Partial Layer Aggregation for Backdoor Defense Against High-Ratio Malicious Clients
  2. 2021Meta Federated Learning
  3. 2023Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions
  4. 2025BackFed: An Efficient & Standardized Benchmark Suite for Backdoor Attacks in Federated Learning
  5. 2023Fedward: Flexible Federated Backdoor Defense Framework with Non-IID Data
  6. 2024Securing Federated Learning against Backdoor Threats with Foundation Model Integration
  7. 2023FedGrad: Mitigating Backdoor Attacks in Federated Learning Through Local Ultimate Gradients Inspection
  8. 2024Foundation Models in Federated Learning: Assessing Backdoor Vulnerabilities