# Optimal Defenses Against Gradient Reconstruction Attacks

arXiv: https://arxiv.org/abs/2411.03746 · HTML: https://mlsanity.com/paper/2411.03746/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 6 Nov 2024.

## Builds on (most cited first, 22 of 22)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training](https://mlsanity.com/paper/1712.01887/) (2017)
- [iDLG: Improved Deep Leakage from Gradients](https://mlsanity.com/paper/2001.02610/) (2020)
- [See through Gradients: Image Batch Recovery via GradInversion](https://mlsanity.com/paper/2104.07586/) (2021)
- [Differentially Private Learning with Adaptive Clipping](https://mlsanity.com/paper/1905.03871/) (2019)
- [Gradient Inversion with Generative Image Prior](https://mlsanity.com/paper/2110.14962/) (2021)
- [Provable Defense against Privacy Leakage in Federated Learning from Representation Perspective](https://mlsanity.com/paper/2012.06043/) (2020)
- [CAFE: Catastrophic Data Leakage in Vertical Federated Learning](https://mlsanity.com/paper/2110.15122/) (2021)
- [Selective Differential Privacy for Language Modeling](https://mlsanity.com/paper/2108.12944/) (2021)
- [Survey: Leakage and Privacy at Inference Time](https://mlsanity.com/paper/2107.01614/) (2021)
- [A Survey on Gradient Inversion: Attacks, Defenses and Future Directions](https://mlsanity.com/paper/2206.07284/) (2022)
- [Trading Off Privacy, Utility and Efficiency in Federated Learning](https://mlsanity.com/paper/2209.00230/) (2022)
- [Defending against Reconstruction Attacks with R'enyi Differential Privacy](https://mlsanity.com/paper/2202.07623/) (2022)
- [Reconstructing Training Data from Model Gradient, Provably](https://mlsanity.com/paper/2212.03714/) (2022)
- [Variance-based Gradient Compression for Efficient Distributed Deep Learning](https://mlsanity.com/paper/1802.06058/) (2018)
- [Understanding Training-Data Leakage from Gradients in Neural Networks for Image Classification](https://mlsanity.com/paper/2111.10178/) (2021)
- [Data Reconstruction Attacks and Defenses: A Systematic Evaluation](https://mlsanity.com/paper/2402.09478/) (2024)
- [Bayesian Cram'er-Rao Bound Estimation with Score-Based Models](https://mlsanity.com/paper/2309.16076/) (2023)

## Abstract (arXiv)

Federated Learning (FL) is designed to prevent data leakage through collaborative model training without centralized data storage. However, it remains vulnerable to gradient reconstruction attacks that recover original training data from shared gradients. To optimize the trade-off between data leakage and utility loss, we first derive a theoretical lower bound of reconstruction error (among all attackers) for the two standard methods: adding noise, and gradient pruning. We then customize these two defenses to be parameter- and model-specific and achieve the optimal trade-off between our obtained reconstruction lower bound and model utility. Experimental results validate that our methods outperform Gradient Noise and Gradient Pruning by protecting the training data better while also achieving better utility.