Leveraging priors via diffusion bridge for time series generation
Park, Jinseong†, Lee, Seungyun†, Jeong, Woojin, Choi, Yujin, Lee, Jaewook. (2026). "Leveraging priors via diffusion bridge for time series generation." KDD 2026.
CV
Education
- Ph.D. in Industrial Engineering, Seoul National University, Feb 2026
- Advisor: Prof. Jaewook Lee
- Dissertation: Trustworthy Generative Model: from privacy to fairness
- B.S. in Industrial Engineering and Mathematics, Yonsei University, Feb 2021
Work Experience
- Postdoctoral Researcher (March 2026 – Present)
- Ulsan National Institute of Science & Technology (UNIST), Korea
- Mentor: Prof. Saerom Park
- Postdoctoral Researcher (April 2026 – Present)
- Nanyang Technological University (NTU), Singapore
- Host: Prof. Jaehong Yoon
Research Interests
- Trustworthy AI: Privacy, Fairness, Robustness
- Generative Models: Diffusion Model, Flow Matching, Large Language Model
Publications
Differentially Private Upsampling for Enhanced Anomaly Detection in Imbalanced Data
Choi, Yujin, Park, Jinseong, Park, Youngjoo, Lee, Jaewook, Byun, Junyoung. (2026). "Differentially Private Upsampling for Enhanced Anomaly Detection in Imbalanced Data." Engineering Applications of Artificial Intelligence.
Multi-Class Support Vector Machine with Differential Privacy
Park, Jinseong, Choi, Yujin, Lee, Jaewook. (2025). "Multi-Class Support Vector Machine with Differential Privacy." NeurIPS 2025.
Temporal consistency ensemble empirical mode decomposition for forecasting practical metal price
Choi, Yujin, Kim, Dongbin, Lee, Jaewook. (2025). "Temporal consistency ensemble empirical mode decomposition for forecasting practical metal price." Engineering Applications of Artificial Intelligence.
Safeguarding Privacy of Retrieval Data against Membership Inference Attacks: Is This Query Too Close to Home?
Choi, Yujin†, Park, Youngjoo†, Byun, Junyoung, Lee, Jaewook, Park, Jinseong. (2025). "Safeguarding Privacy of Retrieval Data against Membership Inference Attacks: Is This Query Too Close to Home?." EMNLP Findings 2025.
Improving the utility of differentially private clustering through dynamical processing
Byun, Junyoung, Choi, Yujin, Lee, Jaewook. (2025). "Improving the utility of differentially private clustering through dynamical processing." Pattern Recognition.
In-distribution public data synthesis with diffusion models for differentially private image classification
Park, Jinseong†, Choi, Yujin†, Lee, Jaewook. (2024). "In-distribution public data synthesis with diffusion models for differentially private image classification." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.
Bayesnam: Leveraging inconsistency for reliable explanations
Kim, Hoki, Park, Jinseong, Choi, Yujin, Lee, Seungyun, Lee, Jaewook. (2024). "Bayesnam: Leveraging inconsistency for reliable explanations." arXiv preprint arXiv:2411.06367.
Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training
Choi, Yujin, Park, Jinseong, Byun, Junyoung, Lee, Jaewook. (2024). "Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training." arXiv preprint arXiv:2412.09842.
Fair Sampling in Diffusion Models through Switching Mechanism
Choi, Yujin†, Park, Jinseong†, Kim, Hoki, Lee, Jaewook, Park, Saerom. (2024). "Fair Sampling in Diffusion Models through Switching Mechanism." Proceedings of the AAAI Conference on Artificial Intelligence.
Privacy-preserving inference resistant to model extraction attacks
Byun, Junyoung, Choi, Yujin, Lee, Jaewook, Park, Saerom. (2024). "Privacy-preserving inference resistant to model extraction attacks." Expert Systems with Applications.
Fast sharpness-aware training for periodic time series classification and forecasting
Park, Jinseong, Kim, Hoki, Choi, Yujin, Lee, Woojin, Lee, Jaewook. (2023). "Fast sharpness-aware training for periodic time series classification and forecasting." Applied Soft Computing.
Efficient differentially private kernel support vector classifier for multi-class classification
Park, Jinseong, Choi, Yujin, Byun, Junyoung, Lee, Jaewook, Park, Saerom. (2023). "Efficient differentially private kernel support vector classifier for multi-class classification." Information Sciences.
Differentially private sharpness-aware training
Park, Jinseong, Kim, Hoki, Choi, Yujin, Lee, Jaewook. (2023). "Differentially private sharpness-aware training." International Conference on Machine Learning.
Stability analysis of sharpness-aware minimization
Kim, Hoki, Park, Jinseong, Choi, Yujin, Lee, Jaewook. (2023). "Stability analysis of sharpness-aware minimization." arXiv preprint arXiv:2301.06308.
Fantastic robustness measures: The secrets of robust generalization
Kim, Hoki, Park, Jinseong, Choi, Yujin, Lee, Jaewook. (2023). "Fantastic robustness measures: The secrets of robust generalization." Advances in Neural Information Processing Systems.
Exploring the effect of multi-step ascent in sharpness-aware minimization
Kim, Hoki, Park, Jinseong, Choi, Yujin, Lee, Woojin, Lee, Jaewook. (2023). "Exploring the effect of multi-step ascent in sharpness-aware minimization." arXiv preprint arXiv:2302.10181.
Exploring diverse feature extractions for adversarial audio detection
Choi, Yujin, Park, Jinseong, Lee, Jaewook, Kim, Hoki. (2023). "Exploring diverse feature extractions for adversarial audio detection." IEEE Access.
Efficient homomorphic encryption framework for privacy-preserving regression
Byun, Junyoung, Park, Saerom, Choi, Yujin, Lee, Jaewook. (2023). "Efficient homomorphic encryption framework for privacy-preserving regression." Applied Intelligence.
Teaching
Scholarship and Fellowships
Scholarship
- Youlchon AI Scholarship, Youlchon AI Star, 2025
- National Science and Technology Scholarship (full tuition), Ministry of Science, Korea, 2019-2020
Fellowship
- Doctoral Student Research Grant, Ministry of Science and ICT, Korea (Graduate Research Fellowship in Science and Engineering), 2023-2025