Firuz Juraev

Sungkyunkwan University

Papers

2

Total Citations

5

H-Index

2

About

Firuz Juraev is an emerging researcher specializing in the security and robustness of deep learning systems, with a particular focus on adversarial machine learning. His work addresses one of the most pressing challenges in modern artificial intelligence: the vulnerability of deep learning models to adversarial attacks — subtle, imperceptible perturbations that can deceive even state-of-the-art neural networks deployed in high-stakes environments. Juraev's most notable contributions include his 2022 paper "Depth, Breadth, and Complexity: Ways to Attack and Defend Deep Learning Models," which has garnered 3 citations, and his 2024 follow-up study offering a multi-dimensional analysis of adversarial threats and defensive strategies, already accumulating 2 citations since publication. Together, these works systematically examine how deep learning models used in critical applications — including self-driving vehicles, surveillance systems, drones, and robotics — can be compromised, and propose structured frameworks for understanding and mitigating these risks. Though still early in his academic career, Juraev demonstrates a consistent and focused research trajectory in AI safety and security. His evolving body of work positions him as a promising voice in the growing field of trustworthy and robust machine learning, an area of increasing importance as AI systems become embedded in safety-critical infrastructure worldwide.

Research Focus

Key Achievements

2
H-Index
2
Papers
5
Total Citations
3
Avg Citations/Paper
🏆 Most Cited Paper
Depth, Breadth, and Complexity: Ways to Attack and Defend Deep Learning Models
3 citations · 2022
📈 Most Prolific Year: 2022 (1 Papers)
🤝 Key Collaborators: 5
🏛 Institutions: Sungkyunkwan University

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago