Self-checking deep neural networks for anomalies and adversaries in deployment

• المؤلفون الرئيسيون: XIAO, Yan, BESCHASTNIKH, Ivan, LIN, Yun, HUNDAL, Rajdeep Singh, XIE, Xiaofei, ROSENBLUM, David S., DONG, Jin Song
• التنسيق: text
• اللغة: English
• منشور في: Institutional Knowledge at Singapore Management University 2022
• الموضوعات: self-checking system; trustworthiness; deep neural networks; adversarial examples; deployment; Artificial Intelligence and Robotics; OS and Networks
• الوصول للمادة أونلاين: https://ink.library.smu.edu.sg/sis_research/7493; https://ink.library.smu.edu.sg/context/sis_research/article/8496/viewcontent/tdsc22_selfchecker.pdf
• المؤسسة: Singapore Management University

Deep Neural Networks (DNNs) have been widely adopted, yet DNN models are surprisingly unreliable, which raises significant concerns about their use in critical domains. In this work, we propose that runtime DNN mistakes can be quickly detected and properly dealt with in deployment, especially in set...