About
I am a last-year Ph.D. student at Seoul National University (SNU), advised by Prof. Jaewook Lee in Statistical Learning & Computational Finance (SLCF) Lab. I am also fulfilling my military service as part of my Ph.D. program.
Prior to this, I received M.S. in Industrial Engineering at SNU and B.S. in Industrial and Management Engineering at Pohang University of Science and Technology (POSTECH).
Topics of interest:
- Robust AI: Effective training frameworks for temporal, private, and limited data. (i) Generative diffusion models under limited data circumstances, such as privacy (CVPR'24) and fairness (AAAI'24). (ii) Modeling temporal time series data for synthetic data augmentation (arXiv) and its real-world applications, such as in finance (Comp' Econ').
- Reliable ML: Privacy-preserving methods to mitigate privacy-utility trade-offs (ICML'23, Information Sciences, CVPR'24). Defense methods against various attacks to address privacy and safety issues in AI model attacks (NeurIPS'21, NeurIPS'23, Pattern Recognition). Neural networks optimization to mitigate the performance gap between training and test accuracies (Applied Soft Computing, ICML'23).
News
-
July 2024. I am attending ICML 2024 in person. See you in Vienna!
-
March 2024. One paper concering differntial privacy with in-distribution public data synthesis using diffusion model is accepted by CVPR 2024. I am attending Seattle in person!
-
January 2024. One paper concering fairness of diffusion model is accepted by AAAI 2024. I am attending Vancouver in person!
-
December 2023. One paper concerning robust generalization is accepted by NeurIPS 2023.
-
July 2023. Two papers concering privacy and generalization are accepted by ICML 2023. I am attending Hawaii in person!
Publications
Most recent publications on Google Scholar.
[J]: Journal, [C]: Conference, [W]: Workshop. † indicates equal contribution.
[Selected papers]
Modeling Asset Price Process: An Approach for Imaging Price Chart with Generative Diffusion Models
Jinseong Park, Hyungjin Ko, Jaewook Lee
[J] Computational Economics, 2024
In-distribution Public Data Synthesis with Diffusion Models for Differentially Private Image Classification
Jinseong Park†, Yujin Choi†, Jaewook Lee
[C] The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024
Fair Sampling in Diffusion Models through Switching Mechanism
Yujin Choi†, Jinseong Park†, Hoki Kim, Jaewook Lee, Saerom Park
[C] Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2024
Fantastic Robustness Measures: The Secrets of Robust Generalization
Hoki Kim, Jinseong Park, Yujin Choi, Jaewook Lee
[C] Advances in Neural Information Processing Systems (NeurIPS), 2023
Differentially Private Sharpness-Aware Training
Jinseong Park, Hoki Kim, Yujin Choi, Jaewook Lee
[C] International Conference on Machine Learning (ICML), 2023
Implicit Jacobian regularization weighted with impurity of probability output
Sungyoon Lee, Jinseong Park, Jaewook Lee
[C] International Conference on Machine Learning (ICML), 2023
Fast sharpness-aware training for periodic time series classification and forecasting
Jinseong Park, Hoki Kim, Yujin Choi, Woojin Lee, Jaewook Lee
[J] Applied Soft Computing, 2023
Generating Transferable Adversarial Examples for Speech Classification
Hoki Kim, Jinseong Park, Jaewook Lee
[J] Pattern Recognition, 2023
Efficient differentially private kernel support vector classifier for multi-class classification
Jinseong Park, Yujin Choi, Junyoung Byun, Jaewook Lee, Saerom Park
[J] Information Sciences, 2023
Towards Better Understanding of Training Certifiably Robust Models against Adversarial Examples
Sungyoon Lee, Woojin Lee, Jinseong Park, Jaewook Lee
[C] Advances in Neural Information Processing Systems (NeurIPS), 2021
[Preprints and all papers]
Leveraging Priors via Diffusion Bridge for Time Series Generation
Jinseong Park, Seungyun Lee, Woojin Jeong, Yujin Choi, Jaewook Lee
Preprint
Stability Analysis of Sharpness-Aware Minimization
Hoki Kim, Jinseong Park, Yujin Choi, Jaewook Lee
Preprint
Exploring the Effect of Multi-step Ascent in Sharpness-Aware Minimization
Hoki Kim, Jinseong Park, Yujin Choi, Jaewook Lee
Preprint
Enhancing non-linear asset volatility forecasting models with investor sentiment and Explainable AI
Seungju Lee, Jinseong Park, Jaewook Lee
[W] Korea Computer Congress (KCC) XAI Workshop, 2023, Best Paper Award (2/37)
Exploring Diverse Feature Extractions for Adversarial Audio Detection
Yujin Choi, Jinseong Park, Jaewook Lee, Hoki Kim
[J] IEEE Access, 2023
Vitæ
-
Seoul, KoreaMar'20 - now
Ph.D. and M.S. in Industrial Engineering - Seoul National University (SNU)
Advised by Prof. Jaewook Lee in Statistical Learning & Computational Finance (SLCF) Lab.
Ph.D. (Mar. 2022 - Present) and M.S. (Mar. 2020 - Feb. 2022). -
Graz, AustriaMar'19 - Aug'19
B.S. in Mechanical Engineering (Study Abroad) - Technische Universität Graz
-
Pohang, KoreaMar'16 - Feb'20
B.S. in Industrial and Management Engineering - Pohang University of Science and Technology (POSTECH)
Experience
[Project] COSMAX Dec. 2023 - Sep. 2024
Deep learning prediction and generative models for color cosmetics
[Project] LNG industry research project with POSCO EnergySep. 2019 - Dec. 2019
Researcher, with Prof. Ribin Seo at POSTECH
[Lecturer] Soongsil UniversitySep. 2024 - Feb. 2025
Analysis of Financial Time Series, Fall Semester 2024, School of Finance
[Invited Talks] DesiloJul. 2024
Deep Learning with Differential Privacy
[Attendee] Graduate Summer School on Algorithmic FairnessJul. 2022
Take the summer school organized by Cynthia Dwork, Guy Rothblum, and Noa Dagan, Institute for Pure & Applied Mathematics (IPAM) at UCLA
[Intern] Industrial Data Engineering & Analytics (IDEA) Lab.Sep. 2019 - Dec. 2019
Research Intern, hosted by Prof. Hyunbo Cho at POSTECH
[Intern] SK TelecomJun. 2018 - Aug. 2018
Intern, R&D Digital Transformation Team