Author name cluster

Yujin Choi

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

2 author rows

EAAI Journal 2026 Journal Article

Differentially private upsampling for enhanced anomaly detection in imbalanced data

Yujin Choi
Jinseong Park
Youngjoo Park
Jaewook Lee
Junyoung Byun

In real-world applications, anomaly detection tasks are critically important. For example, fraud detection for the financial domains and the diagnosis of diseases for the medical domains require highly accurate predictions, as errors can lead to severe consequences. These tasks often rely on sensitive personal data, making it necessary to apply privacy-preserving techniques. However, applying privacy-preserving techniques directly degrades performance. To mitigate this issue, the minority class in an imbalanced dataset can be upsampled to improve balance. In this paper, we propose a differentially private upsampling method using a kernel-based support function for imbalanced datasets. The proposed method employs kernel support vector domain description to estimate the distribution of minority class data under differential privacy constraints, generating synthetic instances based on gradient methods. Additionally, we propose a filtering process that leverages the support function of the majority class data to refine the generated samples without additional privacy loss. Experimental results on real-world datasets demonstrate that the proposed method maintains robust privacy guarantees and achieves superior performance in minority class metrics, comparable to non-private methods.

Details DOI

NeurIPS Conference 2025 Conference Paper

Multi-Class Support Vector Machine with Differential Privacy

Jinseong Park
Yujin Choi
Jaewook Lee

With the increasing need to safeguard data privacy in machine learning models, differential privacy (DP) is one of the major frameworks to build privacy-preserving models. Support Vector Machines (SVMs) are widely used traditional machine learning models due to their robust margin guarantees and strong empirical performance in binary classification. However, applying DP to multi-class SVMs is inadequate, as the standard one-versus-rest (OvR) and one-versus-one (OvO) approaches repeatedly query each data sample when building multiple binary classifiers, thus consuming the privacy budget proportionally to the number of classes. To overcome this limitation, we explore all-in-one SVM approaches for DP, which access each data sample only once to construct multi-class SVM boundaries with margin maximization properties. We propose a novel differentially Private Multi-class SVM (PMSVM) with weight and gradient perturbation methods, providing rigorous sensitivity and convergence analyses to ensure DP in all-in-one SVMs. Empirical results demonstrate that our approach surpasses existing DP-SVM methods in multi-class scenarios.

PDF Details

EAAI Journal 2025 Journal Article

Temporal Consistency Ensemble Empirical Mode Decomposition for forecasting practical metal price

Yujin Choi
Dongbin Kim
Jaewook Lee

Accurately forecasting metal prices is critical to economic, industrial, and energy markets. However, traditional time series models often rely on future data, limiting their real-world applicability. This study found that decomposition methods utilizing future data inflate model performance, and the high accuracy of forecasting models is mainly due to these unrealistic assumptions. In this paper, we propose a novel Temporal Consistency Ensemble Empirical Mode Decomposition (TC-EEMD) method designed for rolling scenarios for practical forecasting models. The performance of the method was evaluated using Support Vector Regression (SVR), Long Short-Term Memory (LSTM) networks, and Transformer on real precious metal price data. The results show that TC-EEMD and hybrid approaches improve forecast accuracy and robustness, mitigating noise dependence and stabilizing forecasts across different industrial applications.

Details DOI

AAAI Conference 2024 Conference Paper

Fair Sampling in Diffusion Models through Switching Mechanism

Yujin Choi
Jinseong Park
Hoki Kim
Jaewook Lee
Saerom Park

Diffusion models have shown their effectiveness in generation tasks by well-approximating the underlying probability distribution. However, diffusion models are known to suffer from an amplified inherent bias from the training data in terms of fairness. While the sampling process of diffusion models can be controlled by conditional guidance, previous works have attempted to find empirical guidance to achieve quantitative fairness. To address this limitation, we propose a fairness-aware sampling method called \textit{attribute switching} mechanism for diffusion models. Without additional training, the proposed sampling can obfuscate sensitive attributes in generated data without relying on classifiers. We mathematically prove and experimentally demonstrate the effectiveness of the proposed method on two key aspects: (i) the generation of fair data and (ii) the preservation of the utility of the generated data.

PDF Details DOI

EAAI Journal 2024 Journal Article

Forecasting personal heat strain under extremely hot environments: Utilizing feature importance in machine learning

SeungWon Seo
Yujin Choi
Choongwan Koo

Since the frequency and intensity of heatwaves are expected to increase due to global warming, it is crucial to establish a simplified approach to preventing personal heat-related illnesses as occupational hazard under extremely hot environments, by taking into account individual differences in heat strain. In light of this, this study proposed a simplified forecast model for personal heat strain under extremely hot environments by utilizing feature importance in machine learning, focused on enhancing its field applicability. Using the 1417 records gathered from the experiments under extremely hot conditions, the simplified model was developed by utilizing four types of machine learning algorithms (i. e. , random forest, extreme gradient boosting, support vector regression, and multi-layer perceptron). As a result, the proposed simplified models with four principal features (i. e. , dry-bulb temperature, radiant temperature, relative humidity, and percentage body fat) were found to be the most reliable, resulting in a small difference of 0. 047 °C compared to the reference model. Since the principal biometric features can be easily measured by a simple and low-cost body composition test (but not with the physical measurement of personal core body temperature) before they are put into the field, the proposed approach will aid in providing more systematic and efficient management system for proactively preventing personal heat-related illnesses. Furthermore, it is expected that the field applicability of the proposed approach can be continuously enhanced by utilizing the accumulated big data gathered from the field-based living-lab projects over a lengthy period.

Details DOI

ICML Conference 2023 Conference Paper

Differentially Private Sharpness-Aware Training

Jinseong Park 0001
Hoki Kim
Yujin Choi
Jaewook Lee 0001

Training deep learning models with differential privacy (DP) results in a degradation of performance. The training dynamics of models with DP show a significant difference from standard training, whereas understanding the geometric properties of private learning remains largely unexplored. In this paper, we investigate sharpness, a key factor in achieving better generalization, in private learning. We show that flat minima can help reduce the negative effects of per-example gradient clipping and the addition of Gaussian noise. We then verify the effectiveness of Sharpness-Aware Minimization (SAM) for seeking flat minima in private learning. However, we also discover that SAM is detrimental to the privacy budget and computational time due to its two-step optimization. Thus, we propose a new sharpness-aware training method that mitigates the privacy-optimization trade-off. Our experimental results demonstrate that the proposed method improves the performance of deep learning models with DP from both scratch and fine-tuning. Code is available at https: //github. com/jinseongP/DPSAT.

Details

NeurIPS Conference 2023 Conference Paper

Fantastic Robustness Measures: The Secrets of Robust Generalization

Hoki Kim
Jinseong Park
Yujin Choi
Jaewook Lee

Adversarial training has become the de-facto standard method for improving the robustness of models against adversarial examples. However, robust overfitting remains a significant challenge, leading to a large gap between the robustness on the training and test datasets. To understand and improve robust generalization, various measures have been developed, including margin, smoothness, and flatness-based measures. In this study, we present a large-scale analysis of robust generalization to empirically verify whether the relationship between these measures and robust generalization remains valid in diverse settings. We demonstrate when and how these measures effectively capture the robust generalization gap by comparing over 1, 300 models trained on CIFAR-10 under the $L_\infty$ norm and further validate our findings through an evaluation of more than 100 models from RobustBench across CIFAR-10, CIFAR-100, and ImageNet. We hope this work can help the community better understand adversarial robustness and motivate the development of more robust defense methods against adversarial attacks.

PDF Details