Robust learning with probabilistic relaxation using hypothesis-test-based sampling

• المؤلف الرئيسي: WANG, Zilin
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2024
• الموضوعات: AI Security; AI Robustness; Deep Learning; Artificial Intelligence and Robotics
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/etd_coll/668; https://ink.library.smu.edu.sg/context/etd_coll/article/1666/viewcontent/GPIS_AY2022_MbR_Wang_Zilin.pdf
• المؤسسة: Singapore Management University

In recent years, deep learning has been a vital tool in various tasks. The performance of a neural network is usually evaluated by empirical risk minimization. However, robustness issues have gained great concern which can be fatal in safety-critical applications. Adversarial training can mitigate t...