Attack as defense: Characterizing adversarial examples using robustness

• المؤلفون الرئيسيون: ZHAO, Zhe, CHEN, Guangke, WANG, Jingyi, YANG, Yiwei, SONG, Fu, SUN, Jun
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2021
• الموضوعات: Deep learning; neural networks; defense; adversarial examples; Software Engineering
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/6213; https://ink.library.smu.edu.sg/context/sis_research/article/7216/viewcontent/attack_as_defense.pdf
• المؤسسة: Singapore Management University

As a new programming paradigm, deep learning has expanded its application to many real-world problems. At the same time, deep learning based software are found to be vulnerable to adversarial attacks. Though various defense mechanisms have been proposed to improve robustness of deep learning softwar...