# Data Poisoning Attacks on Federated Machine Learning

arXiv: https://arxiv.org/abs/2004.10020 · HTML: https://mlsanity.com/paper/2004.10020/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Apr 2020.

## Built on by (most cited first, 30 of 62)

- [Poisoning Language Models During Instruction Tuning](https://mlsanity.com/paper/2305.00944/) (2023)
- [Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning](https://mlsanity.com/paper/2108.10241/) (2021)
- [Federated Learning: Opportunities and Challenges](https://mlsanity.com/paper/2101.05428/) (2021)
- [Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges](https://mlsanity.com/paper/2201.08135/) (2022)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)
- [Byzantine-Robust Federated Learning with Optimal Statistical Rates and Privacy Guarantees](https://mlsanity.com/paper/2205.11765/) (2022)
- [Unleashing the Power of Continual Learning on Non-Centralized Devices: A Survey](https://mlsanity.com/paper/2412.13840/) (2024)
- [Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Survey](https://mlsanity.com/paper/2310.14848/) (2023)
- [Emerging Safety Attack and Defense in Federated Instruction Tuning of Large Language Models](https://mlsanity.com/paper/2406.10630/) (2024)
- [Achieving Byzantine-Resilient Federated Learning via Layer-Adaptive Sparsified Model Aggregation](https://mlsanity.com/paper/2409.01435/) (2024)
- [Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges](https://mlsanity.com/paper/2309.07438/) (2023)
- [Privacy and Trust Redefined in Federated Machine Learning](https://mlsanity.com/paper/2103.15753/) (2021)
- [Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesis](https://mlsanity.com/paper/2210.10886/) (2022)
- [Federated Transfer-Ordered-Personalized Learning for Driver Monitoring Application](https://mlsanity.com/paper/2301.04829/) (2023)
- [A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective](https://mlsanity.com/paper/2311.16065/) (2023)
- [High Dimensional Distributed Gradient Descent with Arbitrary Number of Byzantine Attackers](https://mlsanity.com/paper/2307.13352/) (2023)
- [Turning Federated Learning Systems Into Covert Channels](https://mlsanity.com/paper/2104.10561/) (2021)
- [Can Decentralized Learning be more robust than Federated Learning?](https://mlsanity.com/paper/2303.03829/) (2023)
- [Universal Adversarial Backdoor Attacks to Fool Vertical Federated Learning in Cloud-Edge Collaboration](https://mlsanity.com/paper/2304.11432/) (2023)
- [Byzantine Spectral Ranking](https://mlsanity.com/paper/2211.07902/) (2022)
- [Reputation-Based Federated Learning Defense to Mitigate Threats in EEG Signal Classification](https://mlsanity.com/paper/2401.01896/) (2023)
- [Certified Robustness in Federated Learning](https://mlsanity.com/paper/2206.02535/) (2022)
- [Using Anomaly Detection to Detect Poisoning Attacks in Federated Learning Applications](https://mlsanity.com/paper/2207.08486/) (2022)
- [ModularFed: Leveraging Modularity in Federated Learning Frameworks](https://mlsanity.com/paper/2212.10427/) (2022)
- [Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directions](https://mlsanity.com/paper/2302.06801/) (2023)
- [Privacy Preservation in Artificial Intelligence and Extended Reality (AI-XR) Metaverses: A Survey](https://mlsanity.com/paper/2310.10665/) (2023)
- [Resilience in Online Federated Learning: Mitigating Model-Poisoning Attacks via Partial Sharing](https://mlsanity.com/paper/2403.13108/) (2024)
- [FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?](https://mlsanity.com/paper/2405.13879/) (2024)
- [OCTOPUS: Overcoming Performance andPrivatization Bottlenecks in Distributed Learning](https://mlsanity.com/paper/2105.00602/) (2021)
- [Privacy Preserving Federated Learning with Convolutional Variational Bottlenecks](https://mlsanity.com/paper/2309.04515/) (2023)

## Abstract (arXiv)

Federated machine learning which enables resource constrained node devices (e.g., mobile phones and IoT devices) to learn a shared model while keeping the training data local, can provide privacy, security and economic benefits by designing an effective communication protocol. However, the communication protocol amongst different nodes could be exploited by attackers to launch data poisoning attacks, which has been demonstrated as a big threat to most machine learning models. In this paper, we attempt to explore the vulnerability of federated machine learning. More specifically, we focus on attacking a federated multi-task learning framework, which is a federated learning framework via adopting a general multi-task learning framework to handle statistical challenges. We formulate the problem of computing optimal poisoning attacks on federated multi-task learning as a bilevel program that is adaptive to arbitrary choice of target nodes and source attacking nodes. Then we propose a novel systems-aware optimization method, ATTack on Federated Learning (AT2FL), which is efficiency to derive the implicit gradients for poisoned data, and further compute optimal attack strategies in the federated machine learning. Our work is an earlier study that considers issues of data poisoning attack for federated learning. To the end, experimental results on real-world datasets show that federated multi-task learning model is very sensitive to poisoning attacks, when the attackers either directly poison the target nodes or indirectly poison the related nodes by exploiting the communication protocol.