AGArash Golabi

Arash Golabi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Arash Golabi has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A dual-channel robust deep learning framework for enhanced detection of hardware Trojans via side-channel analysis

    by Arash Golabi, Abdelkarim Erradi, Ahmed Bensaid, Abdulla Al-Ali, Uvais Qidwai

    The detection of Hardware Trojans (HTs) in electronic components is critical to ensuring the security and integrity of electronic systems, as these malicious modifications can leak sensitive information, alter device functionality, or completely disable the device. This study introduces a novel detection method combining deep learning techniques with dual-channel image transformations to identify HTs via Side-Channel Analysis (SCA). Specifically, our approach converts side-channel time series signals, such as power consumption, electromagnetic emissions, and timing data, into dual-channel, image-like representations using Gramian Angular Field (GAF) and reshaping techniques. These transformations allow convolutional neural networks (CNNs), known for their effectiveness in image analysis, to capture subtle and complex anomalous patterns indicative of HTs. We rigorously evaluated our dual-channel methodology using publicly available Advanced Encryption Standard (AES) datasets for HTs provided by TrustHub and IEEE Dataport. Experimental results demonstrate that the proposed approach achieves superior accuracy compared to existing methods, particularly in challenging datasets. Additionally, we assessed the robustness of our model by introducing varying noise levels to simulate real-world operational perturbations such as process variations, aging, and voltage fluctuations. The proposed method maintains high detection accuracy and demonstrates enhanced resilience under noisy conditions, underscoring its practical applicability and effectiveness in detecting sophisticated HT threats.


  • Deep Learning-Based Hardware Trojan Detection via Dual-Path CNN and Markov Transition Field Representations

    by Arash Golabi, Abdelkarim Erradi, Ahmed Bensaid, Abdulla Al-Ali, Uvais Qidwai

    This paper introduces a dual-path deep learning framework specially designed for the efficient detection and classification of Hardware Trojans (HTs) through Side-Channel Analysis (SCA). Using Markov Transition Field (MTF) encoding and a reshaping strategy, the proposed method first converts side-channel time-series signals, including power traces, electromagnetic leaks, and timing data, into two different image-like formats. Detecting subtle Trojan activity requires these representations to capture intricate signal dynamics. Subsequently, each image is processed by a separate convolutional neural network (CNN) branch within the dual-path architecture, with each path optimized for extracting complementary features. To enhance classification performance, the outputs of both CNNs are fused via a dense neural network layer. The dual-path mechanism contributes to improved detection accuracy and robust feature extraction, while the overall architecture supports the classification of specific Trojan types. Evaluation using the publicly available AES Hardware Trojan dataset sourced from TrustHub and IEEE DataPort demonstrates that the proposed model benefits from CNN-based feature learning and outperforms several existing approaches.

  • Open Access

    A dual-stage deep learning approach for robust detection and identification of hardware trojans using monte-carlo dropout

    by Arash Golabi, Abdelkarim Erradi, Ahmed Bensaid, Abdulla Al-Ali, Uvais Qidwai

    Hardware Trojans (HTs) pose a significant threat to the integrity and security of integrated circuits, particularly in critical systems where stealthy hardware modifications can lead to catastrophic consequences. Detecting such Trojans through side-channel analysis (SCA) remains a major challenge due to subtle signal variations and environmental noise. This paper presents a dual-path deep learning framework for the detection and identification of HTs via side-channel analysis. The proposed approach transforms time-series side-channel data- including power consumption, electromagnetic emissions, and timing information-into two distinct image-based representations using Markov Transition Fields (MTF) and a reshaping technique. These transformed representations feed into a two-stage architecture: an Attack Detector, which determines the presence of an HT, and an Attack Identifier, which classifies the specific type of detected HT. To enhance reliability, Monte Carlo Dropout (MCD) is integrated for uncertainty estimation, enabling the framework to flag low-confidence detections and support more robust decision-making. The proposed method is evaluated on publicly available AES hardware Trojan datasets from TrustHub and IEEE Dataport, demonstrating superior accuracy over existing approaches, particularly for complex HT variants with subtle attack signatures. Furthermore, the robustness of the proposed method has been assessed by introducing noise into the validation dataset to simulate real-world operational perturbations such as process variation, aging, and voltage level variations. The results demonstrate the effectiveness and applicability of the dual-path deep learning framework for hardware Trojan detection.


  • Open Access

    Optimal operation of reverse osmosis desalination process with deep reinforcement learning methods

    by Arash Golabi, Abdelkarim Erradi, Hazim Qiblawey, Ashraf Tantawy, Ahmed Bensaid, Khaled Shaban

    The reverse osmosis (RO) process is a well-established desalination technology, wherein energy-efficient techniques and advanced process control methods significantly reduce production costs. This study proposes an optimal real-time management method to minimize the total daily operation cost of an RO desalination plant, integrating a storage tank system to meet varying daily freshwater demand. Utilizing the dynamic model of the RO process, a cascade structure with two reinforcement learning (RL) agents, namely the deep deterministic policy gradient (DDPG) and deep Q-Network (DQN), is developed to optimize the operation of the RO plant. The DDPG agent, manipulating the high-pressure pump, controls the permeate flow rate to track a reference setpoint value. Simultaneously, the DQN agent selects the optimal setpoint value and communicates it to the DDPG controller to minimize the plant’s operation cost. Monitoring storage tanks, permeate flow rates, and water demand enables the DQN agent to determine the required amount of permeate water, optimizing water quality and energy consumption. Additionally, the DQN agent monitors the storage tank’s water level to prevent overflow or underflow of permeate water. Simulation results demonstrate the effectiveness and practicality of the designed RL agents.


  • Reverse osmosis desalination process modeling and simulation with membrane fouling

    by Arash Golabi, Abdelkarim Erradi, Hazim Qiblawey, Ashraf Tantawy, Ahmed Bensaid, Khaled Shaban

    Analyzing the correlation between the key RO operating conditions and performance indicators requires accurate reverse osmosis (RO) model that facilitates under


  • Detecting deception attacks in cyber‐physical linear parameter varying systems with packet loss

    by Arash Golabi, Abdelkarim Erradi, Ashraf Tantawy, Khaled Shaban

    Summary: The increased connectivity of cyber‐physical systems (CPS) to enterprise networks raises challenging security concerns. Detecting attacks on CPS is a vital step to improving their security. Most of the existing attack detectors are for CPS with linear dynamics. In this study, an investigation is made for designing a detector of deception attacks in a cyber‐physical linear parameter varying (LPV) system in the presence of packet loss. A model‐based attack detector is designed to detect deception attacks on output measurements, actuators, or schedule variables. With an unreliable network, the LPV attack detector enhances detection capacity and attenuates disturbances on the detector module to improve detection accuracy. During communication, packet loss results in network unreliability, which is modeled by the Bernoulli process. Stochastic stability is used to determine LPV attack detector parameters. A residual signal is built by comparing the detector's output and the actual sensor measurement and provides the deception attack's essential data. However, the packet loss causes some impulse signals in the residual signal, resulting in false alarms. Therefore, the detector module is equipped with a median filter to suppress packet loss's effect on evaluating the residual signal. Tests and validations of the proposed approach are performed on a two‐tank system and a continuous stirred tank reactor. According to evaluation results conducted on two testbeds, the proposed method accurately detects deception attacks even when there is packet loss.


  • Detecting False Data Injection Attacks in Linear Parameter Varying Cyber-Physical Systems

    by Arash Golabi, Abdelkarim Erradi, Ashraf Tantawy, Khaled Shaban

    In this paper, we investigate the process of detection of False Data Injection (FDI) in a Linear Parameter Varying (LPV) cyber-physical system (CPS). We design a model based FDI detector capable of detecting false data injections on output measurements and scheduling variables. To improve the detection accuracy of FDI attacks, the attack detector design uses the performance metric H_ to maximize the detection capability of the detector module to effectively detect FDI attacks. On the other hand, it uses the $H_{\infty}$ metric to minimize the effect of disturbance on the detector module given an unreliable network. We assume that the network unreliability comes from packet dropout that we modeled as Bernoulli process. The FDI attack detector is designed such that H_ and $H_{\infty}$ performance metrics are maintained despite packet dropout. Based on stochastic stability, we define a set of sufficient Linear Matrix Inequalities (LMI) that we solve as a multi-objective optimization problem to obtain the detector gain. The obtained detector gain is used for estimating the current system state and current output measurement using the system input, manipulated measurements and manipulated scheduling variables. Then, the output of the detector is compared with the actual sensor measurement. The resulting residual signal carries the information about the FDI attack.The proposed approach is tested and validated on a two-tank system. The evaluation results demonstrate that the proposed detector is able to detect FDI attacks.