# Local Differential Privacy for Federated Learning

arXiv: https://arxiv.org/abs/2202.06053 · HTML: https://mlsanity.com/paper/2202.06053/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Feb 2022.

## Built on by (most cited first, 5 of 5)

- [Personalized Privacy-Preserving Framework for Cross-Silo Federated Learning](https://mlsanity.com/paper/2302.12020/) (2023)
- [Shuffled Differentially Private Federated Learning for Time Series Data Analytics](https://mlsanity.com/paper/2307.16196/) (2023)
- [Momentum Gradient Descent Federated Learning with Local Differential Privacy](https://mlsanity.com/paper/2209.14086/) (2022)
- [Local Differential Privacy for Smart Meter Data Sharing](https://mlsanity.com/paper/2311.04544/) (2023)
- [Hijacking Attacks against Neural Networks by Analyzing Training Data](https://mlsanity.com/paper/2401.09740/) (2024)

## Abstract (arXiv)

Advanced adversarial attacks such as membership inference and model memorization can make federated learning (FL) vulnerable and potentially leak sensitive private data. Local differentially private (LDP) approaches are gaining more popularity due to stronger privacy notions and native support for data distribution compared to other differentially private (DP) solutions. However, DP approaches assume that the FL server (that aggregates the models) is honest (run the FL protocol honestly) or semi-honest (run the FL protocol honestly while also trying to learn as much information as possible). These assumptions make such approaches unrealistic and unreliable for real-world settings. Besides, in real-world industrial environments (e.g., healthcare), the distributed entities (e.g., hospitals) are already composed of locally running machine learning models (this setting is also referred to as the cross-silo setting). Existing approaches do not provide a scalable mechanism for privacy-preserving FL to be utilized under such settings, potentially with untrusted parties. This paper proposes a new local differentially private FL (named LDPFL) protocol for industrial settings. LDPFL can run in industrial settings with untrusted entities while enforcing stronger privacy guarantees than existing approaches. LDPFL shows high FL model performance (up to 98%) under small privacy budgets (e.g., epsilon = 0.5) in comparison to existing methods.