Buse G. A. Tekgul
Papers
1
Total Citations
7
H-Index
1
About
Buse G. A. Tekgul is a researcher at the forefront of artificial intelligence safety, specializing in the robustness of deep reinforcement learning (DRL) systems. Her most cited work, "Real-Time Adversarial Perturbations Against Deep Reinforcement Learning Policies: Attacks and Defenses" (2022), has garnered 7 citations and addresses a critical vulnerability in autonomous decision-making. In this study, Tekgul systematically demonstrates how subtle, real-time adversarial perturbations can deceive DRL policies—such as those used in robotics or autonomous navigation—while also proposing novel defense mechanisms to fortify these systems against such attacks. This dual focus on both attack and defense places her work at the heart of the ongoing battle to secure AI agents in dynamic, real-world environments. By bridging the gap between theoretical adversarial machine learning and practical deployment challenges, Tekgul’s contributions are essential for ensuring that DRL-based technologies remain reliable and trustworthy. Her research not only advances the field’s understanding of AI vulnerabilities but also provides actionable solutions for developers and engineers building resilient autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1