Privacy-preserving Federated Learning for Industrial Defect Detection Systems via Differential Privacy and Image Obfuscation

Chia Yu Lin, Yu Chen Yeh, Makena Lu

研究成果: 書貢獻/報告類型會議論文篇章同行評審

摘要

Artificial Intelligence (AI) has been widely used in manufacturing to detect defects. AI models utilize product images to distinguish whether a product is normal or abnormal. If attackers use the model inversion attack to attack AI models, the input images can be roughly restored, resulting in product information leakage. In this paper, we propose a Privacy-preserving Industrial Defect Detection System (PIDS), which includes three image obfuscation methods to hide input image information and uses them to train the model. Federated learning and differential privacy are also applied to ensure that sensitive data remains decentralized and secure, even during training. Federated learning allows the model to be trained across multiple local datasets without centralized data collection, thereby reducing the risk of data exposure. Differential privacy adds another layer of protection by adding randomness to the learning process, making it hard for attackers to extract sensitive information from the trained model. Experiments show that the proposed system can achieve a high accuracy level of 96.5% in defect image classification. Therefore, the proposed system can detect defects accurately and preserve product information in terms of data and models.

原文???core.languages.en_GB???
主出版物標題Proceedings - 2024 IEEE Conference on Artificial Intelligence, CAI 2024
發行者Institute of Electrical and Electronics Engineers Inc.
頁面1136-1141
頁數6
ISBN(電子)9798350354096
DOIs
出版狀態已出版 - 2024
事件2nd IEEE Conference on Artificial Intelligence, CAI 2024 - Singapore, Singapore
持續時間: 25 6月 202427 6月 2024

出版系列

名字Proceedings - 2024 IEEE Conference on Artificial Intelligence, CAI 2024

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???2nd IEEE Conference on Artificial Intelligence, CAI 2024
國家/地區Singapore
城市Singapore
期間25/06/2427/06/24

指紋

深入研究「Privacy-preserving Federated Learning for Industrial Defect Detection Systems via Differential Privacy and Image Obfuscation」主題。共同形成了獨特的指紋。

引用此