On the Detectability of Active Gradient Inversion Attacks in Federated Learning (IEEE S&P '26) - Source Code
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
This artifact accompanies the paper "On the Detectability of Active Gradient Inversion Attacks in Federated Learning," published at the 2026 IEEE Symposium on Security and Privacy (SP). Federated Learning (FL) allows multiple clients to collaboratively train a Machine Learning model while keeping their private data on-site. However, the gradients exchanged during training remain vulnerable to Gradient Inversion Attacks (GIAs), allowing a malicious server to reconstruct the clients' local data. In active attacks, the server deliberately manipulates the global model to facilitate this reconstruction. While earlier active GIAs have been shown to be detectable by clients, recently proposed attacks claim to be far stealthier than previous approaches. This repository provides the official implementation to reproduce our comprehensive analysis of four state-of-the-art active gradient inversion attacks. It also contains the source code for our novel, lightweight client-side detection techniques. These defenses identify statistically improbable weight structures alongside anomalous loss and gradient dynamics, enabling clients to effectively detect active attacks without modifying the standard federated learning protocol. Please refer to the documentation included in the repository for detailed instructions on setting up the environment, running the minimal working example, and reproducing the experimental results. Paper: DOI: 10.1109/SP63933.2026.00193 — IEEE Computer Society, pp. 2346–2365
Fields of Study & Subjects
Privacy-Preserving Technologies in Data
Adversarial Robustness in Machine Learning
Cryptography and Data Security
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 1 April 2026
- Language
- EN