Eric Chan‐Tin

Loyola University Chicago

Papers

1

Total Citations

2

H-Index

1

About

Dr. Eric Chan-Tin is a leading cybersecurity researcher whose work focuses on exposing and fortifying the vulnerabilities of modern machine learning systems. His most cited paper, "Unmasking the Vulnerabilities of Deep Learning Models: A Multi-Dimensional Analysis of Adversarial Attacks and Defenses" (2024, 2 citations), provides a comprehensive framework for understanding how imperceptible adversarial samples can deceive deep learning models used in safety-critical applications like autonomous vehicles and surveillance. This work systematically categorizes attack vectors and defense mechanisms, offering a crucial roadmap for developing more robust AI. Beyond this, Dr. Chan-Tin’s broader research portfolio spans network security, anonymity systems, and privacy-preserving technologies, where he has made significant contributions to understanding and mitigating threats in distributed systems. His impact is evident in the foundational nature of his studies, which are frequently cited by peers seeking to build resilient deep learning architectures. By bridging the gap between theoretical vulnerability analysis and practical defense strategies, Dr. Chan-Tin is helping to ensure that as AI becomes more pervasive, it remains trustworthy and secure against malicious exploitation.

Research Focus

Key Achievements

1
H-Index
1
Papers
2
Total Citations
2
Avg Citations/Paper
🏆 Most Cited Paper
Unmasking the Vulnerabilities of Deep Learning Models: A Multi-Dimensional Analysis of Adversarial Attacks and Defenses
2 citations · 2024
📈 Most Prolific Year: 2024 (1 Papers)
🤝 Key Collaborators: 4
🏛 Institutions: Loyola University Chicago

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 9 days ago