HunminYang.jpeg

I am an Assistant Professor in the Department of AI Cyber Security, at Korea University Sejong Campus. I lead the group on Trustworthy Multimodal AI (TMAI). I am broadly interested in machine learning and computer vision, with a recent focus on security and safety aspects of Generative AI, Physical AI, and Agentic AI. The goal of my research is to develop trustworthy multimodal intelligence to enable safe and reliable model deployment in real-world applications. To achieve this, I work at the intersection of AI and security. I hope to continue making a positive impact on society by enhancing the trustworthiness of AI.

Previously, I was a AI researcher at ADD. I received my PhD in adversarial machine learning at KAIST in 2026, under the supervision of Kuk-Jin Yoon. My PhD thesis focused on the security implications of deep vision models. I received BS and MS also from KAIST in 2012 and 2014.

I am open to new collaborations, so please feel free to contact me! 🙂

News

Sep 1, 2026 👨‍💼 I started to work as an assistant professor at Korea University Sejong Campus!
Jan 26, 2026 📝 One paper accepted to ICLR 2026.
Dec 10, 2025 🎓 I have successfully defended my PhD dissertation!
Feb 26, 2025 📝 One paper accepted to CVPR 2025.
Aug 12, 2024 :trophy: PDCL-Attack selected as oral presentation at ECCV 2024.
Jul 1, 2024 📝 One paper accepted to ECCV 2024.
Dec 9, 2023 📝 One paper accepted to AAAI 2024.
Jul 18, 2023 📝 Two papers accepted to ICCV 2023.
Mar 3, 2022 📝 One paper accepted to CVPR 2022.
Dec 3, 2021 :trophy: I won the National Grant for Defense Research and Development from DAPA.

Experience

Sep, 2026 - Present Korea University Sejong Campus, Sejong, South Korea
Assistant Professor
  • Leading Trustworthy Multimodal AI (TMAI) Lab
Jan, 2020 - Aug, 2026 Agency For Defense Development (ADD), Daejeon, South Korea
Senior AI Researcher
  • Multi-modal LLMs & diffusion models for generative AI
  • Adversarial attack & defense techniques for robust AI
May, 2017 - Dec, 2019 Agency For Defense Development (ADD), Daejeon, South Korea
AI Researcher
  • Synthetic data generation framework for training AI
  • Large-scale AI inference platform with Hadoop-Spark
Feb, 2014 - May, 2017 Agency For Defense Development (ADD), Daejeon, South Korea
Specialized Research Staff (Military Service)

Education

Sep, 2021 - Feb, 2026 Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea
PhD in Mechanical Engineering
  • Research Area: Adversarial Machine Learning
  • Advisor: Kuk-Jin Yoon
Feb, 2012 - Feb, 2014 Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea
MS in Mechanical Engineering
  • Research Area: 3D Sound Perception
  • Advisor: Youngjin Park
Feb, 2011 - Aug, 2011 Royal Melbourne Institute of Technology (RMIT), Melbourne, Australia
Exchange Student (High Distinction)
Feb, 2007 - Feb, 2012 Korea Advanced Institute of Science and Technology (KAIST), Daejeon, South Korea
BS in Mechanical Engineering (Magna Cum Laude)

Selected Publications

  1. Improving Black-Box Generative Attacks via Generator Semantic Consistency
    Jongoh Jeong,  Hunmin Yang, Jaeseok Jeong, and Kuk-Jin Yoon
    International Conference on Learning Representations (ICLR), 2026
    Paper Project Page
  2. Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild
    Junhyeong Cho, Kim Youwang,  Hunmin Yang, and Tae-Hyun Oh
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
    Paper Project Page
  3. Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks
    Hunmin Yang, Jongoh Jeong, and Kuk-Jin Yoon
    European Conference on Computer Vision (ECCV), 2024
    Oral Presentation (top 2.3%)
    Paper Project Page
  4. FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks
    Hunmin Yang*, Jongoh Jeong*, and Kuk-Jin Yoon (*equal contribution)
    Association for the Advancement of Artificial Intelligence (AAAI), 2024
    ICCV Workshop on Adversarial Robustness In the Real World (AROW), 2023
    Paper Project Page
  5. PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
    Junhyeong Cho, Gilhyun Nam, Sungyeon Kim,  Hunmin Yang, and Suha Kwak
    IEEE/CVF International Conference on Computer Vision (ICCV), 2023
    Paper Project Page
  6. ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasion
    Naufal Suryanto, Yongsu Kim, Harashta Tatimma Larasati, Hyoeun Kang, Thi-Thu-Huong Le, Yoonyoung Hong,  Hunmin Yang, Se-Yoon Oh, and Howon Kim
    IEEE/CVF International Conference on Computer Vision (ICCV), 2023
    Paper Project Page
  7. DTA: Physical Camouflage Attacks Using Differentiable Transformation Network
    Naufal Suryanto, Yongsu Kim, Hyoeun Kang, Harashta Tatimma Larasati, Youngyeo Yun, Thi-Thu-Huong Le,  Hunmin Yang, Se-Yoon Oh, and Howon Kim
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
    Paper Project Page

Honors and Awards

  • Defense Science Award, ADD, 2025
    • Adversarial Attack Countermeasures for Robust AI-based Image Analysis Systems
  • Selected as Oral Presentation (top 2.3%), ECCV, 2024
    • Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks
  • National Grant for Defense Research and Development, DAPA, 2021
    • Synthetic Data Generation for Defense AI
  • Defense Science Award, ADD, 2019
    • Improving Distributed Multi-GPU Computing for Large-scale Intelligent Video Analytics
  • High Achievement Award, ADD, 2018
    • Big Data Platform Development and Synthetic Data Generation
  • Excellent Paper Award, KSNVE, 2013
    • Sweet Spot Analysis of Linear Array System with a Large Number of Loudspeakers by Geometrical Approach Method

Professional Services

Conference Reviewer
  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • IEEE/CVF International Conference on Computer Vision (ICCV)
  • European Conference on Computer Vision (ECCV)
  • Advances in Neural Information Processing Systems (NeurIPS)
  • AAAI Conference on Artificial Intelligence (AAAI)
  • ACM Multimedia Conference (MM)
  • Association for Computational Linguistics (ACL)
Journal Reviewer
  • International Journal of Computer Vision (IJCV)
  • IEEE Transactions on Dependable and Secure Computing (TDSC)
Technology Transfer