Eldor Abdukhamidov
Papers
1
Total Citations
3
H-Index
1
About
Eldor Abdukhamidov is a researcher at the forefront of deep learning security, focusing on the critical vulnerabilities of neural networks in high-stakes applications. His work systematically explores the "depth, breadth, and complexity" of adversarial attacks and defenses, addressing how imperceptible perturbations can compromise models used in self-driving vehicles, surveillance, and robotics. In his most cited paper (2022), he provides a comprehensive taxonomy of attack vectors and defensive strategies, offering a foundational roadmap for securing AI systems against adversarial manipulation. With 3 citations to date, this work is gaining recognition as a key reference for researchers hardening deep learning models against real-world threats. Abdukhamidov’s contributions are particularly vital as AI is increasingly deployed in safety-critical domains, where even minor vulnerabilities can have catastrophic consequences. His research bridges the gap between theoretical model robustness and practical deployment challenges, making him a notable voice in the emerging field of adversarial machine learning.
Research Focus
Key Achievements
Top Papers
- 1