Mitigating the Backdoor Attack by Federated Filters for Industrial IoT Applications
| Autor: | Boyu Hou, Ying Zhang, Thar Baker, Zheli Liu, Jiqiang Gao, Xiaojie Guo, Wen Yanlong |
|---|---|
| Rok vydání: | 2022 |
| Předmět: |
Software_OPERATINGSYSTEMS
business.industry Computer science Computer security computer.software_genre Filter (software) Federated learning Computer Science Applications Effective solution Control and Systems Engineering Industrial Internet Electrical and Electronic Engineering Internet of Things business computer Information Systems Backdoor |
| Zdroj: | IEEE Transactions on Industrial Informatics. 18:3562-3571 |
| ISSN: | 1941-0050 1551-3203 |
| Popis: | The federated learning provides an effective solution to train collaborative models over a large scale of participated Industrial Internet of Things (IIoT) applications with the help of a global server, building an intelligent life. However, the federated learning is vulnerable to the backdoor attack from strong malicious participants. The backdoor attack is inconspicuous and may result in devastating consequences. To resist the attack on IIoT applications, we propose the federated backdoor filter defense that can identifying backdoor inputs and restore the data to availability by the blur-label-flipping strategy. We build multiple filters with eXplainable AI (XAI) models on the server and send them to clients randomly, preventing advanced attackers from evading the defense. Our backdoor filters show significant backdoor recognition with the accuracy up to 99%. After the implementation of the blur-label-flipping strategy, victim's local model on suspicious backdoor samples can achieve the accuracy up to 88%. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|