Beomjin Jin

Beomjin Jin

Auto-generated profile, based on publicly available information

Beomjin Jin

Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, Republic of Korea and Purdue University, West Lafayette, Indiana, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
27 March 2023 in IEEE Access
Verified
Journal Article
Open access
BJBeomjin Jin
Beomjin Jin
JCJusop Choi
Jusop Choi
Jin HongJin Hong
Jin Hong
Hyoungshick KimHyoungshick Kim
Hyoungshick Kim
Malware variants are generated using various evasion techniques to bypass malware detectors, so it is important to understand what properties make them evade malware detection techniques. To do this, a framework is proposed to effectively generate fully-working, unseen malware samples on Windows portable executable (PE) files with various perturbations such as code obfuscation and benign section addition. Using this framework, we were able to bypass various commercial anti-malware solutions (e.g., BitDefender, AVG, Kaspersky, and Avast) using the generated malware variants, with up to 86% more evasiveness than the original malware samples, and up to 28% more evasive compared with our previously proposed solution FUMVar. Our results are useful in terms of improving malware detection techniques, by analyzing different perturbations and their effectiveness, which leads to a better understanding of how malware variants could be generated that are more evasive and which malware categories they belong to. We found that the most effective perturbation is the code obfuscation using XOR – the malware variants generated by the code obfuscation can evade the detection of 28 anti-malware engines on average. Therefore, our experimental results and observations would be useful to develop anti-malware solutions that would be effective in detecting malware variants that have not been seen previously.



12 April 2026
Verified
Conference Paper
Open access
CLChaejin Lim
Chaejin Lim
KLKiho Lee
Kiho Lee
BJBeomjin Jin
Beomjin Jin
HBHeewon Baek
Heewon Baek
Hyoungshick KimHyoungshick Kim
Hyoungshick Kim
While machine learning has significantly advanced ad and tracker detection, existing systems face critical challenges in practice. They are vulnerable to adversarial attacks (57-92% evasion rates), fail to generalize to unseen domains due to data contamination, and suffer performance degradation over time, requiring costly retraining. To address these challenges, we present AdVersa, a client-side framework for robust and practical ad and tracker blocking. AdVersa leverages novel, hard-to-perturb latent features from code and URL embeddings to deliver state-of-the-art performance. On a 2.74M-request dataset, our results show that AdVersa achieves a 98.23% F1 score, twice the robustness against adversarial attacks, and strong generalization to unseen domains (91.47% F1 score). For sustainable protection, we demonstrate that a low-cost pseudo-labeling strategy can maintain near-optimal accuracy, reducing maintenance overhead by over 99.8% compared to filter-list curation. Finally, we implement AdVersa as a lightweight, standalone client-side application that ensures user privacy by operating without external dependencies.


17 April 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
BJBeomjin Jin
Beomjin Jin
YDYejin Do
Yejin Do
SJSeyoung Jin
Seyoung Jin
JOJungho Oh
Jungho Oh
SYSeungwoo Yoo
Seungwoo Yoo
Hyoungshick KimHyoungshick Kim
Hyoungshick Kim
The rapid growth of complex malware has intensified the burden on security analysts, prompting demand for scalable solutions to automate malware analysis and threat intelligence (CTI) reporting. We introduce CTIGen, a novel framework that automates CTI report generation by integrating large language models (LLMs) with traditional static and dynamic analysis tools. Replicating expert workflows, CTIGen first performs dynamic behavior extraction, then conducts targeted static inspection guided by those behaviors, and finally synthesizes findings into structured, ATT&CK-aligned reports using a graph-based reasoning module. Our evaluation results show that CTIGen achieves strong recall across key tasks: 0.87 for function identification, 0.95 for behavior extraction, 0.36 for function-to-behavior mapping, and 0.58 for IoC identification. Notably, CTIGen identifies malicious functions and their corresponding behaviors within 8 minutes per sample, substantially reducing manual analysis time. Furthermore, CTIGen identifies 121 additional malicious functions with correct behavioral semantics beyond those documented in human-written reports. In ATT&CK technique identification, CTIGen achieves an 77.23% accuracy, demonstrating reliable alignment with annotated ATT&CK techniques. Interestingly, reports generated by CTIGen are more fluent than human-written ones and are rated more useful in a user study. These results demonstrate the potential of LLM-based multi-stage automation for generating accurate and scalable malware threat intelligence.