I-Te Danny Hung

Papers

Total Citations

H-Index

About

I-Te Danny Hung is a prominent researcher in the intersection of artificial intelligence, cybersecurity, and robotics, with a particular focus on the vulnerabilities of deep reinforcement learning (DRL) systems. His most cited work, "Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learning" (2020, 25 citations), makes a critical contribution by demonstrating how strategically timed adversarial perturbations can effectively compromise DRL-based autonomous systems, such as those used in robot navigation and continuous control tasks. This research highlights the fragility of self-adaptive neural networks in real-world applications, offering both a cautionary perspective and a foundation for developing more robust learning algorithms. Hung’s work is notable for bridging the gap between theoretical adversarial machine learning and practical robotic security, providing actionable insights for engineers designing resilient autonomous systems. His findings are particularly relevant to fields like autonomous driving and industrial robotics, where system-level attacks could have severe consequences. Through his research, Hung has established himself as a key voice in the emerging dialogue on AI safety and adversarial robustness.