# GANcrop: A Contrastive Defense Against Backdoor Attacks in Federated Learning

arXiv: https://arxiv.org/abs/2405.20727 · HTML: https://mlsanity.com/paper/2405.20727/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 18 references that are in the map.
- First posted on arXiv 31 May 2024.

## Builds on (most cited first, 12 of 12)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [SimCSE: Simple Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2104.08821/) (2021)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks](https://mlsanity.com/paper/1805.12185/) (2018)
- [Federated Learning on Non-IID Data Silos: An Experimental Study](https://mlsanity.com/paper/2102.02079/) (2021)
- [Exploiting Unintended Feature Leakage in Collaborative Learning](https://mlsanity.com/paper/1805.04049/) (2018)
- [Can You Really Backdoor Federated Learning?](https://mlsanity.com/paper/1911.07963/) (2019)
- [Rethinking the Trigger of Backdoor Attack](https://mlsanity.com/paper/2004.04692/) (2020)
- [Abnormal Client Behavior Detection in Federated Learning](https://mlsanity.com/paper/1910.09933/) (2019)
- [Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions](https://mlsanity.com/paper/2303.02213/) (2023)

## Built on by (most cited first, 1 of 1)

- [Backdoor Attacks on Multi-modal Contrastive Learning](https://mlsanity.com/paper/2601.11006/) (2026)

## Abstract (arXiv)

With heightened awareness of data privacy protection, Federated Learning (FL) has attracted widespread attention as a privacy-preserving distributed machine learning method. However, the distributed nature of federated learning also provides opportunities for backdoor attacks, where attackers can guide the model to produce incorrect predictions without affecting the global model training process. This paper introduces a novel defense mechanism against backdoor attacks in federated learning, named GANcrop. This approach leverages contrastive learning to deeply explore the disparities between malicious and benign models for attack identification, followed by the utilization of Generative Adversarial Networks (GAN) to recover backdoor triggers and implement targeted mitigation strategies. Experimental findings demonstrate that GANcrop effectively safeguards against backdoor attacks, particularly in non-IID scenarios, while maintaining satisfactory model accuracy, showcasing its remarkable defensive efficacy and practical utility.