A Survey on Gradient Inversion: Attacks, Defenses and Future Directions

A Survey on Gradient Inversion: Attacks, Defenses and Future Directions

Rui Zhang, Song Guo, Junxiao Wang, Xin Xie, Dacheng Tao

Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence
Survey Track. Pages 5678-5685. https://doi.org/10.24963/ijcai.2022/791

Recent studies have shown that the training samples can be recovered from gradients, which are called Gradient Inversion (GradInv) attacks. However, there remains a lack of extensive surveys covering recent advances and thorough analysis of this issue. In this paper, we present a comprehensive survey on GradInv, aiming to summarize the cutting-edge research and broaden the horizons for different domains. Firstly, we propose a taxonomy of GradInv attacks by characterizing existing attacks into two paradigms: iteration- and recursion-based attacks. In particular, we dig out some critical ingredients from the iteration-based attacks, including data initialization, model training and gradient matching. Second, we summarize emerging defense strategies against GradInv attacks. We find these approaches focus on three perspectives covering data obscuration, model improvement and gradient protection. Finally, we discuss some promising directions and open problems for further research.
Keywords:
Survey Track: AI Ethics, Trust, Fairness
Survey Track: Uncertainty in AI
Survey Track: Machine Learning