JinYeong Bak

JinYeong Bak

Auto-generated profile, based on publicly available information

JinYeong Bak

Sungkyunkwan University, Suwon, Republic of Korea

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 October 2023 in Mechanical Systems and Signal Processing
Verified
Journal Article
Closed access
VVVan Vy
Van Vy
YLYunwoo Lee
Yunwoo Lee
JBJinYeong Bak
JinYeong Bak
SPSolmoi Park
Solmoi Park
SPSeunghee Park
Seunghee Park
Hyungchul YoonHyungchul Yoon
Hyungchul Yoon

21 June 2022 in IEEE Access
Verified
Journal Article
Open access
DTDai Tran
Dai Tran
MPMinsoo Park
Minsoo Park
YJYuntae Jeon
Yuntae Jeon
JBJinyeong Bak
Jinyeong Bak
Seunghee ParkSeunghee Park
Seunghee Park
An effective forest-fire response is critical for minimizing the losses caused by forest fires. The purpose of this study is to construct a model for early fire detection and damage area estimation for response systems based on deep learning. First, we implement neural architecture search-based object detection (DetNAS) for searching optimal backbone. Backbone networks play a crucial role in the application of deep learning-based models, as they have a significant impact on the performance of the model. A large-scale fire dataset with approximately 400,000 images is used to train and test object-detection models. Then, the searched light-weight backbone is compared with well-known backbones, such as ResNet, VoVNet, and FBNetV3. In addition, we propose damage area estimation method using Bayesian neural network (BNN), data pertaining to six years of historical forest fire events are employed to estimate the damaged area. Subsequently, a weather API is used to match the recorded events. A BNN model is used as a regression model to estimate the damaged area. Additionally, the trained model is compared with other widely used regression models, such as decision trees and neural networks. The Faster R-CNN with a searched backbone achieves a mean average precision of 27.9 on 40,000 testing images, outperforming existing backbones. Compared with other regression models, the BNN estimates the damage area with less error and increased generalization. Thus, both proposed models demonstrate their robustness and suitability for implementation in real-world systems.

28 October 2022 in International Journal of Applied Earth Observation and Geoinformation
Verified
Journal Article
Open access
MPMinsoo Park
Minsoo Park
DTDai Tran
Dai Tran
JBJinyeong Bak
Jinyeong Bak
Seunghee ParkSeunghee Park
Seunghee Park

10 July 2023
Verified
Conference Paper
Open access
HKHyun-Jin Kim
Hyun-Jin Kim
JBJinyeong Bak
Jinyeong Bak
KCKyunghyun Cho
Kyunghyun Cho
HKHyungjoon Koo
Hyungjoon Koo
Reverse engineering of a stripped binary has a wide range of applications, yet it is challenging mainly due to the lack of contextually useful information within. Once debugging symbols (e.g., variable names, types, function names) are discarded, recovering such information is not technically viable with traditional approaches like static or dynamic binary analysis. We focus on a function symbol name recovery, which allows a reverse engineer to gain a quick overview of an unseen binary. The key insight is that a well-developed program labels a meaningful function name that describes its underlying semantics well. In this paper, we present AsmDepictor, the Transformer-based framework that generates a function symbol name from a set of assembly codes (i.e., machine instructions), which consists of three major components: binary code refinement, model training, and inference. To this end, we conduct systematic experiments on the effectiveness of code refinement that can enhance an overall performance. We introduce the per-layer positional embedding and Unique-softmax for AsmDepictor so that both can aid to capture a better relationship between tokens. Lastly, we devise a novel evaluation metric tailored for a short description length, the Jaccard* score. Our empirical evaluation shows that the performance of AsmDepictor by far surpasses that of the state-of-the-art models up to around 400%. The best AsmDepictor model achieves an F1 of 71.5 and Jaccard* of 75.4.

1 January 2023
Verified
Conference Paper
Open access
PDF file
DKDongjun Kang
Dongjun Kang
JPJoonsuk Park
Joonsuk Park
YJYohan Jo
Yohan Jo
JBJinYeong Bak
JinYeong Bak
Dongjun Kang, Joonsuk Park, Yohan Jo, JinYeong Bak. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

6 March 2025 in SuperIntelligence - Robotics - Safety & Alignment
Verified
Journal Article
Open access
PDF file
HKHyunJin Kim
HyunJin Kim
XYXiaoyuan Yi
Xiaoyuan Yi
JBJinYeong Bak
JinYeong Bak
JYJing Yao
Jing Yao
JLJianxun Lian
Jianxun Lian
XXXing Xie
Xing Xie
The emergence of large language models (LLMs) has sparkedthe discussion on Artificial Superintelligence (ASI), a hypothetical AI system surpassing human intelligence. Though ASI is still hypothetical and far from current AI capabilities, existing alignment methods struggle to guide such advanced AI ensure its safety in the future. It is essential to discuss the alignment of such AI now. Superalignment, the alignment of AI at superhuman levels of capability systems with human values and safety requirements, aims to address two primary goals: scalability in supervision to provide high-quality guidance signals and robust governance to ensure alignment with human values. In this survey, we review the original scalable oversight problem and corresponding methods and potential solutions for superalignment. Specifically, we introduce the challenges and limitations of current alignment paradigms in addressing the superalignment problem. Then we review scalable oversight methods for superalignment. Finally, we discuss the key challenges and propose pathways for the safe and continual improvement of future AI systems. By comprehensively reviewing the current literature, our goal is provide a systematical introduction of existing methods, analyze their strengths and limitations, and discuss potential future directions.