Hyunjun Kim

Hyunjun Kim

Auto-generated profile, based on publicly available information

Hyunjun Kim

Department of Electrical and Computer Engineering and Inter-university Semiconductor Research Center, Seoul National University, Republic of Korea

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
6 August 2021 in IEEE Access
Verified
Journal Article
Open access
HKHyunjun Kim
Hyunjun Kim
SASunwoo Ahn
Sunwoo Ahn
WHWhoi Ree Ha
Whoi Ree Ha
HKHyunjae Kang
Hyunjae Kang
DKDong Seong Kim
Dong Seong Kim
Yunheung PaekYunheung Paek
Yunheung Paek
Recently, using artificial neural networks (ANNs) for network intrusion detection systems (NIDSs) has drawn much attention from security researchers. The capability of ANNs to learn patterns from numerous data helps detect attacks on networked systems. Moreover, to effectively monitor a newly emerging networked system consisting of distributed subsystems, such as edge, Internet of Things (IoT), and fog, recent studies have proposed an ANN-based distributed NIDS , where multiple ANNs are deployed to local gateways. To meet the incessant demand for high accuracy, ANN-based NIDSs have become complicated and heavy. With local gateways being small and low-end, such ANNs cannot be executed. Some researchers have proposed optimized algorithms to balance detection accuracy and runtime performance to solve this problem. For example, Kitsune empirically proved its efficiency, but a recent study reveals that Kitsune has limitations. In particular, Kitsune fails at identifying host-oriented attacks, which pretend to be benign during packet delivery but incur malicious behavior on destination devices. Panop is a novel ANN-based NIDS for a distributed network system that aims to detect malicious packets, including host-oriented attacks, while remaining sufficiently lightweight to be executed by low-end devices. Thus, the Panop ANN is designed to comprehensively learn network and device behaviors related to packet transactions in an IoT network. According to the experiments, Panop can detect host-oriented and other attacks with reasonably high accuracy with little degradation in runtime performance compared to the state-of-the-art NIDS for distributed network environments.

16 October 2023
Verified
Conference Paper
Open access
HKHyunjun Kim
Hyunjun Kim
YCYungi Cho
Yungi Cho
YLYounghan Lee
Younghan Lee
HBHo Bae
Ho Bae
Yunheung PaekYunheung Paek
Yunheung Paek
Clustered federated learning (CFL) is an advanced technique in the field of federated learning (FL) that addresses the issue of catastrophic forgetting caused by non-independent and identically distributed (non-IID) datasets. CFL achieves this by clustering clients based on the similarity of their datasets and training a global model for each cluster. Despite the effectiveness of CFL in mitigating performance degradation resulting from non-IID datasets, the potential risk of privacy leakages in CFL has not been thoroughly studied. Previous work evaluated the risk of privacy leakages in FL using the property inference attack (PIA), which extracts information about unintended properties (i.e., attributes that differ from the target attribute of the global model’s main task). In this paper, we explore the potential risk of unintended property leakage in CFL by subjecting it to both passive and active PIAs. Our empirical analysis shows that the passive PIA performance on CFL is substantially better than that on FL in terms of the attack AUC score. Moreover, we propose an enhanced active PIA method tailored for CFL to improve the attack performance. Our method introduces a scale-up parameter that amplifies the impact of malicious local updates, resulting in better performance than the previous technique. Furthermore, we demonstrate that the vulnerability of CFL can be alleviated by applying differential privacy (DP) mechanisms at the client-level. Unlike previous works, which have shown that applying DP to FL can induce a high utility loss, our empirical results indicate that DP can be used as a defense mechanism in CFL, leading to a better trade-off between privacy and utility.

1 August 2019 in Journal of Extension
Verified
Journal Article
Open access
PDF file
MCMary Caskey
Mary Caskey
BCBonnie Christiansen
Bonnie Christiansen
SHStephanie Hakes
Stephanie Hakes
PHPatti Held
Patti Held
HKHyunjun Kim
Hyunjun Kim
Reporting requirements for capturing data on the delivery of Supplemental Nutrition Assistance Program Education (SNAP-Ed) have evolved. University of Minnesota (U of M) Extension developed the SNAP Education Evaluation and Database System (SEEDS) to capture unduplicated participant information for SNAP-Ed programming conducted by U of M Extension across the state of Minnesota. The data collected in SEEDS have utility related to both managing programs and measuring the success of programs at local, regional, and state levels. Extension professionals in other states may benefit from developing a similar centralized database for collecting SNAP-Ed data.

22 May 2023 in IEEE Access
Verified
Journal Article
Open access
WHWhoi Ree Ha
Whoi Ree Ha
HKHyunjun Kim
Hyunjun Kim
Yunheung PaekYunheung Paek
Yunheung Paek
Techniques, like pruning and dimension reduction, and characteristics of data for applications, like natural language processing and object detection, introduce sparsity in deep learning models inherently. Sparse tensor accelerators leverage sparsity (0’s) in data in order to remove ineffectual computations to speed-up overall run-time. Numerous approaches have been suggested by other researchers such as encoding, decoding, non-zero extraction, load balancing and etc. However, since each implementation requires specialized hardware to accommodate the unique features, the design space becomes much larger compared to regular tensor accelerators when designing a new sparse accelerator. Also these features are hard to compare since the efficiency varies according to application and data sparsity. In this paper, we classify and support the modeling of popularly used features for sparse tensor accelerators. These features enable us to model much larger design space and to estimate their cost more accurately. Library support for these features is also included to make early-stage exploration more realistic. Overall, our experiments show that we can analytically estimate the previously un-modeled components with 93% accuracy on average and provide 19 features as a library support.

11 September 2025 in Future Generation Computer Systems
Verified
Journal Article
Open access
HKHyunjun Kim
Hyunjun Kim
WHWhoi Ree Ha
Whoi Ree Ha
YLYongseok Lee
Yongseok Lee
DLDongju Lee
Dongju Lee
JLJongwon Lee
Jongwon Lee
YPYunheung Paek
Yunheung Paek