Challenges and countermeasures for adversarial attacks on deep reinforcement learning

• Main Authors: Ilahi, Inaam, Usama, Muhammad, Qadir, Junaid, Janjua, Muhammad Umar, Al-Fuqaha, Ala, Hoang, Dinh Thai, Niyato, Dusit
• Other Authors: School of Computer Science and Engineering
• Format: Article
• Language: English
• Published: 2022
• Subjects: Engineering::Computer science and engineering; Adversarial Machine Learning; Cyber-Security
• Online Access: https://hdl.handle.net/10356/163971
• Institution: Nanyang Technological University

Deep reinforcement learning (DRL) has numerous applications in the real world, thanks to its ability to achieve high performance in a range of environments with little manual oversight. Despite its great advantages, DRL is susceptible to adversarial attacks, which precludes its use in real-life crit...