# DP-SIGNSGD: When Efficiency Meets Privacy and Robustness

arXiv: https://arxiv.org/abs/2105.04808 · HTML: https://mlsanity.com/paper/2105.04808/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 May 2021.

## Built on by (most cited first, 11 of 11)

- [Joint Privacy Enhancement and Quantization in Federated Learning](https://mlsanity.com/paper/2208.10888/) (2022)
- [Federated Learning with Sparsified Model Perturbation: Improving Accuracy under Client-Level Differential Privacy](https://mlsanity.com/paper/2202.07178/) (2022)
- [Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam](https://mlsanity.com/paper/2202.06009/) (2022)
- [Dropout is NOT All You Need to Prevent Gradient Leakage](https://mlsanity.com/paper/2208.06163/) (2022)
- [Differential Privacy Meets Neural Network Pruning](https://mlsanity.com/paper/2303.04612/) (2023)
- [Pre-Pruning and Gradient-Dropping Improve Differentially Private Image Classification](https://mlsanity.com/paper/2306.11754/) (2023)
- [FedMPDD: Communication-Efficient Federated Learning with Privacy Preservation Attributes via Projected Directional Derivative](https://mlsanity.com/paper/2512.20814/) (2025)
- [FedDiSC: A Computation-efficient Federated Learning Framework for Power Systems Disturbance and Cyber Attack Discrimination](https://mlsanity.com/paper/2304.03640/) (2023)
- [PAUSE: Low-Latency and Privacy-Aware Active User Selection for Federated Learning](https://mlsanity.com/paper/2503.13173/) (2025)
- [Hi-SAFE: Hierarchical Secure Aggregation for Lightweight Federated Learning](https://mlsanity.com/paper/2511.18887/) (2025)
- [FERRET: Private Deep Learning Faster And Better Than DPSGD](https://mlsanity.com/paper/2506.05416/) (2025)

## Abstract (arXiv)

Federated learning (FL) has emerged as a promising collaboration paradigm by enabling a multitude of parties to construct a joint model without exposing their private training data. Three main challenges in FL are efficiency, privacy, and robustness. The recently proposed SIGNSGD with majority vote shows a promising direction to deal with efficiency and Byzantine robustness. However, there is no guarantee that SIGNSGD is privacy-preserving. In this paper, we bridge this gap by presenting an improved method called DP-SIGNSGD, which can meet all the aforementioned properties. We further propose an error-feedback variant of DP-SIGNSGD to improve accuracy. Experimental results on benchmark image datasets demonstrate the effectiveness of our proposed methods.