Byeonggil Jung

Samsung SDI

Master's in Engineering

(Advisor: Prof. Sangkyun Lee [Lab])

[6] An LSTM-Attention Based Model Robust to Input Variations for Source Code Vulnerability Detection, [url]
Kwanyoung Jeong, Byeonggil Jung, Sebeom Cheon, Hyoju Nam, Insub Lee, Namhoon Jung, Kyutae Cho, Sangkyun Lee*,
KIISE Transactions on Computing Practices (KCI), 30 (3), 105-114.

[5] Anomaly Candidate Extraction and Detection for automatic quality inspection of metal casting products
using high-resolution images, [url]
Byeonggil Jung, Heegon You, Sangkyun Lee*,
Journal of Manufacturing Systems (SCIE, IF 12.1), 67, 229-241.

[4] Transparent and Explainable Vision Transformer,
Kwanyoung Jeong, Junhyung Kwon, Byeonggil Jung, Jeonghyun Lee, Sungmin Han, Sangkyun Lee*,
Korea Software Congress, Jeju.

[3] Abnormal Data Augmentation Method Using Perturbation Based on Hypersphere for Semi-Supervised
Anomaly Detection, [url]
Byeonggil Jung, Junhyung Kwon, Dongjun Min, Sangkyun Lee*,
Journal of The Korea Institute of Information Security and Cryptology (KCI), 32, 4, 647-660.

[2] Anomaly Detection in Multi-Host Environment Based on Federated Hypersphere Classifier [url]
Junhyung Kwon, Byeonggil Jung, Hyungil Lee, Sangkyun Lee*,
Electronics (SCIE, IF 2.9), 11(10), 1529.

[1] Adversarial Attacks to Neural Networks on Manufacturing Product Image Data
Byeonggil Jung, Sangkyun Lee*,
Conference on Information Security and Cryptography, (Best paper excellence award).

[4] Electronic apparatus and anomaly detection method thereof,
Junhyung Kwon, Byeonggil Jung, Sangkyun Lee*.
(Application No. 10-2022-0087490)

[3] Method of extracting optimal defect candidate based on pixel intensity of difference image between original image
and reconstructed image,
Byeonggil Jung, Heegon You, Sangkyun Lee*.
(Application No. 10-2021-0170178)

[2] Method of improving false detection of image-based defect detection reflecting statistical property of manufactured product inspection area,
Byeonggil Jung, Heegon You, Sangkyun Lee*.
(Application No. 10-2021-0170177)

[1] Method of detecting defect of manufactured product based on high-resolution image using autoencoder and convolutional
neural network,
Byeonggil Jung, Heegon You, Sangkyun Lee*.
(Application No. 10-2021-0170176)

Vision inspection for automatic quality control of metal casting products

Detecting malicious behaviors using system log data in multi-host environments

Predicting fine dust for air quality forecasting

Software analysis and testing, to reduce False Positive Rate (FPR)

Samsung DS Expert

Database

Security System Development

Research in Data Science 2

Classification Based Anomaly Detection for General Data

Bayesian Optimization

MetaPoison: Practical General-purpose Clean-label Data Poisoning

Gaussian Process

Learning and Evaluating Representations for Deep One-Class Classification

Using Self-Supervised Learning Can Improve Model Robustness and Uncertainty

Timeseries Anomaly Detection using Temporal Hierarchical One-Class Network

DROCC: Deep Robust One-Class Classification

An Integrated Method for Anomaly Detection From Massive System Logs

Anomaly Detection (Comprehensive)

Transfer-Based Semantic Anomaly Detection

Throwing Darts in the Dark Detecting Bots with Limited Data using Neural Data Augmentation

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances

SySeVR: A Framework for Using Deep Learning to Detect Software Vulnerabilities