Deep Leakage from Gradients

By Ligeng Zhu, Zhijian Liu, Song Han. 2019

3,062 citations recorded by the source corpus.

Exchanging gradients is a widely used method in modern multi-node machine learning system (e.g., distributed training, collaborative learning). For a long time, people believed that gradients are safe to share: i.e., the training data will not be leaked by gradient exchange. However, we show that it is possible to obtain the private training data from the publicly shared gradients. We name this leakage as Deep Leakage from Gradient and empirically validate the effectiveness on both computer vision and natural language processing tasks. Experimental results show that our attack is much stronger than previous approaches: the recovery is pixel-wise accurate for images and token-wise matching for texts. We want to raise people's awareness to rethink the gradient's safety. Finally, we discuss several possible strategies to prevent such deep leakage. The most effective defense method is gradient pruning.

Subfields: Artificial Intelligence, Safety, Robustness & Interpretability, Privacy & Security

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Qiang Yang
  2. Philip S. Yu
  3. Percy Liang
  4. Quoc V. Le
  5. Yoshua Bengio
  6. Mohit Bansal
  7. Dacheng Tao
  8. Jianfeng Gao

In Safety, Robustness & Interpretability

  1. Bo Li
  2. Xingjun Ma
  3. Tom Goldstein
  4. Aleksander Madry
  5. Dawn Song
  6. Dimitris Tsipras
  7. Nicholas Carlini
  8. Matthias Hein

In Privacy & Security

  1. Qiang Yang
  2. Yang Liu
  3. Chaoyang He
  4. Murali Annavaram
  5. Basak Guler
  6. Yan Kang
  7. Amir Salman Avestimehr
  8. Philip S. Yu

Citations in the corpus