Toward secure and efficient deep learning inference in dependable IoT systems

• Main Authors: Qiu, Han, Zheng, Qinkai, Zhang, Tianwei, Qiu, Meikang, Memmi, Gerard, Lu, Jialiang
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2021
• Subjects: Engineering::Computer science and engineering; Internet of Things; Sensors
• Online Access: https://hdl.handle.net/10356/148325
• Institution: Nanyang Technological University

The rapid development of deep learning (DL) enables resource-constrained systems and devices [e.g., Internet of Things (IoT)] to perform sophisticated artificial intelligence (AI) applications. However, AI models, such as deep neural networks (DNNs), are known to be vulnerable to adversarial example...