# AGRAMPLIFIER: Defending Federated Learning Against Poisoning Attacks Through Local Update Amplification

arXiv: https://arxiv.org/abs/2311.06996 · HTML: https://mlsanity.com/paper/2311.06996/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 60 references that are in the map.
- First posted on arXiv 13 Nov 2023.

## Builds on (most cited first, 30 of 35)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [RISE: Randomized Input Sampling for Explanation of Black-box Models](https://mlsanity.com/paper/1806.07421/) (2018)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [Fine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks](https://mlsanity.com/paper/1901.08584/) (2019)
- [Local Model Poisoning Attacks to Byzantine-Robust Federated Learning](https://mlsanity.com/paper/1911.11815/) (2019)
- [Federated Learning in Mobile Edge Networks: A Comprehensive Survey](https://mlsanity.com/paper/1909.11875/) (2019)
- [Analyzing Federated Learning through an Adversarial Lens](https://mlsanity.com/paper/1811.12470/) (2018)
- [FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping](https://mlsanity.com/paper/2012.13995/) (2020)
- [The Hidden Vulnerability of Distributed Learning in Byzantium](https://mlsanity.com/paper/1802.07927/) (2018)
- [Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning](https://mlsanity.com/paper/1804.00308/) (2018)
- [Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization](https://mlsanity.com/paper/1708.08689/) (2017)
- [FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clients](https://mlsanity.com/paper/2207.09209/) (2022)
- [CRFL: Certifiably Robust Federated Learning against Backdoor Attacks](https://mlsanity.com/paper/2106.08283/) (2021)
- [Learning how to explain neural networks: PatternNet and PatternAttribution](https://mlsanity.com/paper/1705.05598/) (2017)
- [Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging](https://mlsanity.com/paper/1909.05125/) (2019)
- [Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learning](https://mlsanity.com/paper/2112.14468/) (2021)
- [LoMar: A Local Defense Against Poisoning Attack on Federated Learning](https://mlsanity.com/paper/2201.02873/) (2022)
- [Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realization](https://mlsanity.com/paper/2202.01971/) (2022)

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

- [Not All Edges are Equally Robust: Evaluating the Robustness of Ranking-Based Federated Learning](https://mlsanity.com/paper/2503.08976/) (2025)
- [Hybrid Reputation Aggregation: A Robust Defense Mechanism for Adversarial Federated Learning in 5G and Edge Network Environments](https://mlsanity.com/paper/2509.18044/) (2025)
- [Performance Guaranteed Poisoning Attacks in Federated Learning: A Sliding Mode Approach](https://mlsanity.com/paper/2505.16403/) (2025)
- [Enhancing the Effectiveness and Durability of Backdoor Attacks in Federated Learning through Maximizing Task Distinction](https://mlsanity.com/paper/2509.18904/) (2025)
- [ARES: Scalable and Practical Gradient Inversion Attack in Federated Learning through Activation Recovery](https://mlsanity.com/paper/2603.17623/) (2026)

## Abstract (arXiv)

The collaborative nature of federated learning (FL) poses a major threat in the form of manipulation of local training data and local updates, known as the Byzantine poisoning attack. To address this issue, many Byzantine-robust aggregation rules (AGRs) have been proposed to filter out or moderate suspicious local updates uploaded by Byzantine participants. This paper introduces a novel approach called AGRAMPLIFIER, aiming to simultaneously improve the robustness, fidelity, and efficiency of the existing AGRs. The core idea of AGRAMPLIFIER is to amplify the "morality" of local updates by identifying the most repressive features of each gradient update, which provides a clearer distinction between malicious and benign updates, consequently improving the detection effect. To achieve this objective, two approaches, namely AGRMP and AGRXAI, are proposed. AGRMP organizes local updates into patches and extracts the largest value from each patch, while AGRXAI leverages explainable AI methods to extract the gradient of the most activated features. By equipping AGRAMPLIFIER with the existing Byzantine-robust mechanisms, we successfully enhance the model's robustness, maintaining its fidelity and improving overall efficiency. AGRAMPLIFIER is universally compatible with the existing Byzantine-robust mechanisms. The paper demonstrates its effectiveness by integrating it with all mainstream AGR mechanisms. Extensive evaluations conducted on seven datasets from diverse domains against seven representative poisoning attacks consistently show enhancements in robustness, fidelity, and efficiency, with average gains of 40.08%, 39.18%, and 10.68%, respectively.