Professor Simon Sungil Woo is an Associate Professor of Computer Science and Engineering at Sungkyunkwan University (SKKU). His research focuses on AI security, privacy, anomaly detection, multimedia forensics, deepfake detection, machine learning, and human-centered data science. He leads the DASH Lab and previously worked at NASA’s Jet Propulsion Laboratory.
Publications (8)
2026
Toward Trustworthy Digital Healthcare: A System-Level Convergence of IoMT, Large Language Models, and Explainable AI
Information Fusion
Information Fusion
·
01 May 2026
·
doi:10.1016/j.inffus.2026.104507
2025
Stealthy Query-Efficient OpaqueAttack Against Interpretable Deep Learning
IEEE Transactions on Reliability
·
01 Sep 2025
·
doi:10.1109/TR.2025.3551717
2024
Hardening Interpretable Deep Learning Systems: Investigating Adversarial Threats and Defenses
IEEE TDSC
IEEE Transactions on Dependable and S...
·
01 Jul 2024
·
doi:10.1109/TDSC.2023.3341090
The Impact of Model Variations on the Robustness of Deep Learning Models in Adversarial Settings
2024 Silicon Valley Cybersecurity Con...
·
17 Jun 2024
·
doi:10.1109/SVCC61185.2024.10637362
Impact of Architectural Modifications on Deep Learning Adversarial Robustness
arXiv
·
06 May 2024
·
arxiv:2405.01934
2023
Unveiling Vulnerabilities in Interpretable Deep Learning Systems with Query-Efficient Black-box Attacks
arXiv
·
25 Jul 2023
·
arxiv:2307.11906
Microbial Genetic Algorithm-based Black-box Attack against Interpretable Deep Learning Systems
arXiv
·
14 Jul 2023
·
arxiv:2307.06496
2022
Interpretations Cannot Be Trusted: Stealthy and Effective Adversarial Perturbations against Interpretable Deep Learning
arXiv
·
30 Nov 2022
·
arxiv:2211.15926