Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Hosein Mohammadi Makrani has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    FaRAccel: FPGA-Accelerated Defense Architecture for Efficient Bit-Flip Attack Resilience in Transformer Models

    by Najmeh Nazari, Banafsheh Saber Latibari, Elahe Hosseini, Fatemeh Movafagh, Chongzhou Fang, Hosein Mohammadi Makrani, Kevin Immanuel Gubbi, Abhijit Mahalanobis, Setareh Rafatirad, Hossein Sayadi, et al.

    Forget and Rewire (FaR) methodology has demonstrated strong resilience against Bit-Flip Attacks (BFAs) on Transformer-based models by obfuscating critical parameters through dynamic rewiring of linear layers. However, the application of FaR introduces non-negligible performance and memory overheads, primarily due to the runtime modification of activation pathways and the lack of hardware-level optimization. To overcome these limitations, we propose FaRAccel, a novel hardware accelerator architecture implemented on FPGA, specifically designed to offload and optimize FaR operations. FaRAccel integrates reconfigurable logic for dynamic activation rerouting, and lightweight storage of rewiring configurations, enabling low-latency inference with minimal energy overhead. We evaluate FaRAccel across a suite of Transformer models and demonstrate substantial reductions in FaR inference latency and improvement in energy efficiency, while maintaining the robustness gains of the original FaR methodology. To the best of our knowledge, this is the first hardware-accelerated defense against BFAs in Transformers, effectively bridging the gap between algorithmic resilience and efficient deployment on real-world AI platforms.

  • Open Access

    Architectural Whispers: Robust Machine Learning Models Fingerprinting via Frequency Throttling Side-Channels

    by Najmeh Nazari, Chongzhou Fang, Hosein Mohammadi Makrani, Behnam Omidi, Mahdi Eslamimehr, Setareh Rafatirad, Avesta Sasan, Hossein Sayadi, Khaled N. Khasawneh, Houman Homayoun

    Machine Learning (ML) security practices include hiding ML model architectures to protect intellectual property and prevent attacks. We introduce a novel fingerprinting attack using frequency throttling-based Side-Channel Attack (SCA) to detect an ML model's architecture family by converting power side-channel data into timing variations. This method involves using adversary kernels and a time series ML classifier to discern the architecture from execution time patterns during model operation. We achieved up to 96% accuracy in identifying known ML models' architecture families under Ring 0 privileges and we demonstrated its effectiveness across different platforms. Moreover, our code is publicly available 1.


  • Adversarial Attacks Against Machine Learning-Based Resource Provisioning Systems

    by Najmeh Nazari, Hosein Mohammadi Makrani, Chongzhou Fang, Behnam Omidi, Setareh Rafatirad, Hossein Sayadi, Khaled N. Khasawneh, Houman Homayoun

    Microarchitectural attacks, such as side-channel, exploit shared resources to leak sensitive information. Performing microarchitectural attacks on the cloud is possible once the attacker’s virtual machine (VM) is co-located with the victim’s VM. Hence, the co-location requirement with the victim limits the practicality of microarchitectural attacks on the cloud. In this work, we demonstrate that resource provisioning systems (RPSs) can be exploited to solve the co-location challenge of microarchitectural attacks in the cloud by deploying adversarial evasion attacks on RPSs to co-locate attackers’ VMs with victims’ VMs. Moreover, we discuss the adaptability of defense techniques proposed against adversarial attacks in the image classification domain on the RPSs.


  • Accelerated Machine Learning for On-Device Hardware-Assisted Cybersecurity in Edge Platforms

    by Hosein Mohammadi Makrani, Zhangying He, Setareh Rafatirad, Hossein Sayadi

    Internet of Things (IoT) as an area of tremendous impact, potential, and growth has emerged with the advent of smart homes, smart cities, and smart everything. In the age of IoT, edge devices have taken on greater importance, driving the need for more intelligence and advanced services at the network edge. Since edge devices are limited in compute, storage, and network capacity, they are easy to compromise, more exposed to attackers, and more vulnerable than standard computing systems such as PCs and servers. While several software-based countermeasures have been proposed, they require high computing power and resources that edge devices do not possess. Moreover, modern threats have become more complex and severe, requiring a level of security that can only be provided at the hardware level. In this paper, we realize an efficient hardware-assisted attack detection mechanism for edge devices through effective High Level Synthesize (HLS) optimization techniques. To this end, we propose OptiEdge, a machine learning-guided hardware-assisted resource and timing estimation tool that can effectively reduce the design space exploration for edge devices’ design. This is achieved by analyzing suitability of different machine learning algorithms used for detection and how they affect hardware implementation overheads. By providing a comprehensive analysis of the accuracy, performance, and hardware efficiency of different ML algorithms, our work can assist researchers investigating this field of cybersecurity.


  • Security Threats in Cloud Rooted from Machine Learning-Based Resource Provisioning Systems

    by Hosein Mohammadi Makrani, Hossein Sayadi, Najmeh Nazari, Houman Homayoun


  • Open Access

    Towards Accurate Run-Time Hardware-Assisted Stealthy Malware Detection: A Lightweight, yet Effective Time Series CNN-Based Approach

    by Hossein Sayadi, Yifeng Gao, Hosein Mohammadi Makrani, Jessica Lin, Paulo Cesar Costa, Setareh Rafatirad, Houman Homayoun

    According to recent security analysis reports, malicious software (a.k.a. malware) is rising at an alarming rate in numbers, complexity, and harmful purposes to compromise the security of modern computer systems. Recently, malware detection based on low-level hardware features (e.g., Hardware Performance Counters (HPCs) information) has emerged as an effective alternative solution to address the complexity and performance overheads of traditional software-based detection methods. Hardware-assisted Malware Detection (HMD) techniques depend on standard Machine Learning (ML) classifiers to detect signatures of malicious applications by monitoring built-in HPC registers during execution at run-time. Prior HMD methods though effective have limited their study on detecting malicious applications that are spawned as a separate thread during application execution, hence detecting stealthy malware patterns at run-time remains a critical challenge. Stealthy malware refers to harmful cyber attacks in which malicious code is hidden within benign applications and remains undetected by traditional malware detection approaches. In this paper, we first present a comprehensive review of recent advances in hardware-assisted malware detection studies that have used standard ML techniques to detect the malware signatures. Next, to address the challenge of stealthy malware detection at the processor’s hardware level, we propose StealthMiner, a novel specialized time series machine learning-based approach to accurately detect stealthy malware trace at run-time using branch instructions, the most prominent HPC feature. StealthMiner is based on a lightweight time series Fully Convolutional Neural Network (FCN) model that automatically identifies potentially contaminated samples in HPC-based time series data and utilizes them to accurately recognize the trace of stealthy malware. Our analysis demonstrates that using state-of-the-art ML-based malware detection methods is not effective in detecting stealthy malware samples since the captured HPC data not only represents malware but also carries benign applications’ microarchitectural data. The experimental results demonstrate that with the aid of our novel intelligent approach, stealthy malware can be detected at run-time with 94% detection performance on average with only one HPC feature, outperforming the detection performance of state-of-the-art HMD and general time series classification methods by up to 42% and 36%, respectively.


  • Adaptive-HMD: Accurate and Cost-Efficient Machine Learning-Driven Malware Detection using Microarchitectural Events

    by Yifeng Gao, Hosein Mohammadi Makrani, Mehrdad Aliasgari, Amin Rezaei, Jessica Lin, Houman Homayoun, Hossein Sayadi

    To address the high complexity and computational overheads of conventional software-based detection techniques, Hardware Malware Detection (HMD) has shown promising results as an alternative anomaly detection solution. HMD methods apply Machine Learning (ML) classifiers on microarchitectural events monitored by built-in Hardware Performance Counter (HPC) registers available in modern microprocessors to recognize the patterns of anomalies (e.g., signatures of malicious applications). Existing hardware malware detection solutions have mainly focused on utilizing standard ML algorithms to detect the existence of malware without considering an adaptive and cost-efficient approach for online malware detection. Our comprehensive analysis across a wide range of malicious software applications and different branches of machine learning algorithms indicates that the type of adopted ML algorithm to detect malicious applications at the hardware level highly correlates with the type of the examined malware, and the ultimate performance evaluation metric (F-measure, robustness, latency, detection rate/cost, etc.) to select the most efficient ML model for distinguishing the target malware from benign program. Therefore, in this work we propose Adaptive-HMD, an accurate and cost-efficient machine learning-driven framework for online malware detection using low-level microarchitectural events collected from HPC registers. Adaptive-HMD is equipped with a lightweight tree-based decision-making algorithm that accurately selects the most efficient ML model to be used for the inference in online malware detection according to the users' preference and optimal performance vs. cost (hardware overhead and latency) criteria. The experimental results demonstrate that Adaptive-HMD achieves up to 94% detection rate (F-measure) while improving the cost-efficiency of ML-based malware detection by more than 5X as compared to existing ensemble-based malware detection methods.