Moving target defense for embedded deep visual sensing against adversarial examples

• Main Authors: Song, Qun, Yan, Zhenyu, Tan, Rui
• Other Authors: School of Computer Science and Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2020
• Subjects: Engineering::Computer science and engineering; Software and Application Security; Neural Networks
• Online Access: https://hdl.handle.net/10356/136723
• Institution: Nanyang Technological University

Deep learning-based visual sensing has achieved attractive accuracy but is shown vulnerable to adversarial example attacks. Specifically, once the attackers obtain the deep model, they can construct adversarial examples to mislead the model to yield wrong classification results. Deployable adversari...