Jang-Eui Hong

Dr. Jang-Eui Hong

orcid

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
27 November 2024 in Artificial Intelligence Review
Verified
Journal Article
Open access
PDF file
AIAhmed Dawod Mohammed Ibrahum
Ahmed Dawod Mohammed Ibrahum
MHManzoor Hussain
Manzoor Hussain
JHJang-Eui Hong
Jang-Eui Hong
The integration of Deep Learning (DL) algorithms in Autonomous Vehicles (AVs) has revolutionized their precision in navigating various driving scenarios, ranging from anti-fatigue safe driving to intelligent route planning. Despite their proven effectiveness, concerns regarding the safety and reliability of DL algorithms in AVs have emerged, particularly in light of the escalating threat of adversarial attacks, as emphasized by recent research. These digital or physical attacks present formidable challenges to AV safety, relying extensively on collecting and interpreting environmental data through integrated sensors and DL. This paper addresses this pressing issue through a systematic survey that meticulously explores robust adversarial attacks and defenses, specifically focusing on DL in AVs from a safety perspective. Going beyond a review of existing research papers on adversarial attacks and defenses, the paper introduces a safety scenarios taxonomy matrix Inspired by SOTIF designed to augment the safety of DL in AVs. This matrix categorizes safety scenarios into four distinct areas and classifies attacks into those areas in three scenarios, along with two defense scenarios. Furthermore, the paper investigates the testing and evaluation measurements critical for assessing attacks in the context of DL for AVs. It further explores the dynamic landscape of datasets and simulation platforms. This contribution significantly enriches the ongoing discourse surrounding the assurance of safety and reliability in autonomous vehicles, especially in the face of continually evolving adversarial challenges.

23 November 2021 in Automated Software Engineering
Verified
Journal Article
Closed access
PDF file
MHManzoor Hussain
Manzoor Hussain
Nazakat AliNazakat Ali
Nazakat Ali
JHJang-Eui Hong
Jang-Eui Hong

6 December 2018 in Computers
Verified
Journal Article
Open access
PDF file
Nazakat AliNazakat Ali
Nazakat Ali
JHJang-Eui Hong
Jang-Eui Hong
Cyber-physical systems have emerged as a new engineering paradigm, which combine the cyber and physical world with comprehensive computational and analytical tools to solve complex tasks. In cyber-physical systems, components are developed to detect failures, prevent failures, or mitigate the failures of a system. Sensors gather real-time data as an input to the system for further processing. Therefore, the whole cyber-physical system depends on sensors to accomplish their tasks and the failure of one sensor may lead to the failure of the whole system. To address this issue, we present an approach that utilizes the Failure Modes, Effects, and Criticality Analysis, which is a prominent hazard analysis technique to increase the understanding of risk and failure prevention. In our approach, we transform the Failure Modes, Effects, and Criticality Analysis model into a UML(Unified Modeling Language) class diagram, and then a knowledge base is constructed based on the derived UML class diagram. Finally, the UML class diagram is used to build an ontology. The proposed approach employs a 5C architecture for smart industries for its systematic application. Lastly, we use a smart home case study to validate our approach.

Verified
Journal Article
Open access
PDF file
MHManzoor Hussain
Manzoor Hussain
JHJang-Eui Hong
Jang-Eui Hong
The perception system is a safety-critical component that directly impacts the overall safety of autonomous driving systems (ADSs). It is imperative to ensure the robustness of the deep-learning model used in the perception system. However, studies have shown that these models are highly vulnerable to the adversarial perturbation of input data. The existing works mainly focused on studying the impact of these adversarial attacks on classification rather than regression models. Therefore, this paper first introduces two generalized methods for perturbation-based attacks: (1) We used naturally occurring noises to create perturbations in the input data. (2) We introduce a modified square, HopSkipJump, and decision-based/boundary attack to attack the regression models used in ADSs. Then, we propose a deep-autoencoder-based adversarial attack detector. In addition to offline evaluation metrics (e.g., F1 score and precision, etc.), we introduce an online evaluation framework to evaluate the robustness of the model under attack. The framework considers the reconstruction loss of the deep autoencoder that validates the robustness of the models under attack in an end-to-end fashion at runtime. Our experimental results showed that the proposed adversarial attack detector could detect square, HopSkipJump, and decision-based/boundary attacks with a true positive rate (TPR) of 93%.

6 November 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
AIAhmed Dawod Mohammed Ibrahum
Ahmed Dawod Mohammed Ibrahum
ZSZhengyu Shang
Zhengyu Shang
JHJang-Eui Hong
Jang-Eui Hong
Kolmogorov–Arnold Networks (KANs) are a novel class of neural network architectures based on the Kolmogorov–Arnold representation theorem, which has demonstrated potential advantages in accuracy and interpretability over Multilayer Perceptron (MLP) models. This paper comprehensively evaluates the robustness of various KAN architectures—including KAN, KAN-Mixer, KANConv_KAN, and KANConv_MLP—against adversarial attacks, which constitute a critical aspect that has been underexplored in current research. We compare these models with MLP-based architectures such as MLP, MLP-Mixer, and ConvNet_MLP across three traffic sign classification datasets: GTSRB, BTSD, and CTSD. The models were subjected to various adversarial attacks (FGSM, PGD, CW, and BIM) with varying perturbation levels and were trained under different strategies, including standard training, adversarial training, and Randomized Smoothing. Our experimental results demonstrate that KAN-based models, particularly the KAN-Mixer, exhibit superior robustness to adversarial attacks compared to their MLP counterparts. Specifically, the KAN-Mixer consistently achieved lower Success Attack Rates (SARs) and Degrees of Change (DoCs) across most attack types and datasets while maintaining high accuracy on clean data. For instance, under FGSM attacks with ϵ=0.01, the KAN-Mixer outperformed the MLP-Mixer by maintaining higher accuracy and lower SARs. Adversarial training and Randomized Smoothing further enhanced the robustness of KAN-based models, with t-SNE visualizations revealing more stable latent space representations under adversarial perturbations. These findings underscore the potential of KAN architectures to improve neural network security and reliability in adversarial settings.

3 September 2020 in IEEE Access
Verified
Journal Article
Open access
Nazakat AliNazakat Ali
Nazakat Ali
MHManzoor Hussain
Manzoor Hussain
JHJang-Eui Hong
Jang-Eui Hong
Cyber-Physical System (CPS) is co-engineered interacting networks of physical and computational components that operate on different spatial and temporal scales. The safety goal of a single CPS is usually achieved by applying hazard analysis techniques and by following the standard processes defined in ISO 26262 and IEC 61508. However, the safety property may not be satisfied when multiple CPSs collaborate due to complexity, uncertainty, and variability. Therefore, a technique that would provide a hazardous-free collaboration for multiple CPSs is required to preserve sustainability. In this paper, we analyze the hazards arising due to variabilities in collaborative CPSs. We extend the hazard analysis techniques (FTA, FMEA, and ETA) to explore hazards with variability and developed a fault traceability graph from our extended techniques to trace the faults considered by multiple hazard analyses in collaborative CPSs with variability. To justify our proposed approach, a case study on the human rescue robot system was conducted to analyze hazards emerging as a result of variabilities. Finally, a tool (CPS Tracer) was developed to model the FTA, ETA, and FMEA with variability (v_FTA, v_FMEA, and v_ETA), and generates the fault traceability graph (v_FTG) that represents fault propagation route.