Xiaojun Ren
Papers
2
Total Citations
25
H-Index
2
About
Xiaojun Ren is a leading researcher at the intersection of artificial intelligence, cybersecurity, and edge-cloud collaborative systems. His work primarily focuses on the security and privacy vulnerabilities of Deep Reinforcement Learning (DRL), a critical subfield of AI where agents learn optimal behaviors through environmental interaction. Ren’s most-cited paper, “Security and Privacy Issues in Deep Reinforcement Learning: Threats and Countermeasures” (2024), has garnered 22 citations, providing a comprehensive taxonomy of adversarial attacks and defensive strategies that threaten DRL’s deployment in high-stakes domains like autonomous driving and robotics. This work has become an essential reference for researchers seeking to fortify AI systems against exploitation. Beyond security, Ren has advanced visual location estimation for edge-cloud collaborative IoT, as seen in his paper “Efficient and precise visual location estimation by effective priority matching-based pose verification” (2024). Here, he introduced a priority-matching algorithm that dramatically improves pose verification speed and accuracy, enabling real-time, resource-constrained applications. Ren’s contributions bridge foundational AI safety with practical, scalable IoT solutions, establishing him as a pivotal voice in building trustworthy, efficient autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2