Corpus ID: 216056279

A Framework for Evaluating Gradient Leakage Attacks in Federated Learning

@article{Wei2020AFF,
  title={A Framework for Evaluating Gradient Leakage Attacks in Federated Learning},
  author={Wenqi Wei and Ling Liu and Margaret Loper and Ka-Ho Chow and M. Gursoy and S. Truex and Yanzhao Wu},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.10397}
}
  • Wenqi Wei, Ling Liu, +4 authors Yanzhao Wu
  • Published 2020
  • Computer Science, Mathematics
  • ArXiv
  • Federated learning (FL) is an emerging distributed machine learning framework for collaborative model training with a network of clients (edge devices). FL offers default client privacy by allowing clients to keep their sensitive data on local devices and to only share local training parameter updates with the federated server. However, recent studies have shown that even sharing local parameter updates from a client to the federated server may be susceptible to gradient leakage attacks and… CONTINUE READING
    8 Citations
    Privacy Leakage of Real-World Vertical Federated Learning
    Layer-wise Characterization of Latent Information Leakage in Federated Learning
    R-GAP: Recursive Gradient Attack on Privacy
    Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attacks
    • 1
    • Highly Influenced
    • PDF
    Robust Deep Learning Ensemble against Deception
    • 1
    • PDF
    FedML: A Research Library and Benchmark for Federated Machine Learning
    • 9
    • PDF
    Scalable and Communication-efficient Decentralized Federated Edge Learning with Multi-blockchain Framework

    References

    SHOWING 1-10 OF 48 REFERENCES
    Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning
    • 95
    • PDF
    Inverting Gradients - How easy is it to break privacy in federated learning?
    • 16
    • Highly Influential
    • PDF
    Differentially Private Federated Learning: A Client Level Perspective
    • 244
    • PDF
    How To Backdoor Federated Learning
    • 215
    • PDF
    Exploiting Unintended Feature Leakage in Collaborative Learning
    • 189
    • Highly Influential
    • PDF
    LDP-Fed: federated learning with local differential privacy
    • 6
    • PDF
    Federated Machine Learning
    • 228
    • PDF
    Federated Learning with Non-IID Data
    • 222
    • PDF
    Privacy-Preserving Deep Learning: Revisited and Enhanced
    • 42
    Federated Learning: Strategies for Improving Communication Efficiency
    • 893
    • PDF