Moving target defense for embedded deep visual sensing against adversarial examples

• المؤلفون الرئيسيون: Song, Qun, Yan, Zhenyu, Tan, Rui
• مؤلفون آخرون: School of Computer Science and Engineering
• التنسيق: Conference or Workshop Item
• اللغة: English
• منشور في: 2020
• الموضوعات: Engineering::Computer science and engineering; Software and Application Security; Neural Networks
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/136723

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...