RYRozhin Yasaei

Rozhin Yasaei

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

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


Rozhin Yasaei has a total of 30 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    FedLLM4HW: Carbon-Aware Federated Triage of Hardware Weaknesses in LLM-Generated Verilog Code

    by Parsa Mirfasihi, Arthur Kim, Hariharan Ramesh, Josh Dean, Melika Akbarsharifi, Roxana Akbarsharifi, John Martin Encinas, Pratik Satam, Jyotikrishna Dass, Rozhin Yasaei, et al.

  • Open Access

    Circuits as Graphs: A Review of Graph Learning for Secure and Trustworthy Hardware

    by Afjal Hossan Sarower, Soheil Salehi, Rozhin Yasaei

    Modern Integrated Circuits (ICs) are highly interconnected, making graph representation a natural foundation for hardware security analysis. In recent years, graph-based approaches have gained significant traction in addressing a wide range of hardware security challenges, starting from classical subgraph matching to advanced Graph Neural Network (GNN) models. This paper presents a comprehensive review of graph-centric methods across key domains, including hardware trojan detection and localization, intellectual property piracy and watermark protection, side-channel leakage assessment, and hardware vulnerability analysis. We first discuss how hardware designs can be modeled using different graph modalities and how these representations enable machine learning models to capture structural and functional properties.We then organize existing studies into a unified taxonomy linking problem type, graph formulation, and learning approach. Furthermore, we highlight hardware design to graph conversion tools, datasets, performance trends, and open issues in scalability, explainability, and resilience to adversarial manipulation. Finally, the paper outlines promising research directions such as multi-view graph representations, cross-level GNN integration, effective trojan-node localization, and trustworthy graph learning for secure-by-design hardware. Overall, this review positions graph-based learning as a central enabler for the next generation of hardware security methodologies.

  • Stealthy Hardware Trojans in AI Accelerators: Attacks on Transformer, Convolutional Neural Network, and Systolic Architectures

    by Harish Kumar Dharavath, Banafsheh Saber Latibari, Kevin Immanuel Gubbi, Muhtasim Alam Chowdhury, Sujan Ghimire, Rozhin Yasaei, Pratik Satam, Avesta Sasan, Houman Homayoun, Soheil Salehi

    Transformers, the backbone of Generative AI (GenAI), have shown tremendous success in different fields, leading to the adaptation of hardware accelerators for Transformers. While much attention has been focused on software-level backdoor attacks, such as model or data extraction, hardware vulnerabilities have received less focus. This paper proposes stealthy and practical HTs on attention-based accelerators that cause accuracy degradation. Three novel HTs are presented and evaluated. We use the Adaptable Butterfly Transformer Hardware Accelerator as the victim design to show the impact of embedding HTs. Our results indicate an accuracy degradation of 5% to 91% based on varying numbers of HTs. Additionally, we conduct a preliminary investigation into the impacts of HT on other accelerator architectures, including Convolutional Neural Network (CNN) and systolic-array-based designs.

  • Open Access

    Graph Deviation Network for Anomaly Detection and Localization in Additive Manufacturing Systems

    by Rozhin Yasaei, Ashley Sayuri Masuda, Yasamin Moghaddas, Mohammad Abdullah Al Faruque

    Additive Manufacturing (AM) has revolutionized industries by enabling the production of complex, customized products with unparalleled efficiency. However, the increasing reliance on AM in critical sectors such as aerospace, healthcare, and defense has exposed it to significant cybersecurity and reliability challenges, including intellectual property theft, process sabotage, and data tampering. These vulnerabilities as well as reliability issues can compromise product integrity, safety, and operational continuity, posing severe risks to both industry and national security. In this work, we propose a novel methodology for modeling the AM process chain as a Cyber-Physical System (CPS) using multi-modal data structured in a graph format. Our methodology leverages Graph Neural Networks (GNNs) to detect and localize anomalies across diverse data modalities, enabling precise identification of both the nature and source of attack/fault. By integrating data fusion, advanced anomaly classification, and localization techniques, our solution provides a robust methodology for enhancing the security and reliability of AM processes, ensuring their safe deployment in critical applications. Furthermore, the proposed technique is adaptable to other industrial systems, underscoring its potential for broader impact in securing critical infrastructure.

  • Context-Aware Adaptive Anomaly Detection in IoT Systems

    by Rozhin Yasaei, Mohammad Abdullah Al Faruque


  • Golden Reference-Free Hardware Trojan Localization Using Graph Convolutional Network

    by Rozhin Yasaei, Sina Faezi, Mohammad Abdullah Al Faruque

    The globalization of the integrated circuit (IC) supply chain has moved most of the design, fabrication, and testing process from a single trusted entity to various untrusted third-party entities worldwide. The risk of using untrusted third-Party Intellectual Property (3PIP) is the possibility for adversaries to insert malicious modifications known as Hardware Trojans (HTs). These HTs can compromise the integrity, deteriorate the performance, deny the service, and alter the functionality of the design. While numerous HT detection methods have been proposed in the literature, the crucial task of HT localization is overlooked. Moreover, a few existing HT localization methods have several weaknesses: reliance on a golden reference, inability to generalize for all types of HT, lack of scalability, low localization resolution, and manual feature engineering/property definition. To overcome their shortcomings, we propose a novel, golden reference-free HT localization method at the pre-silicon stage by leveraging graph convolutional network (GCN). In this work, we convert the circuit design into its intrinsic data structure, graph, and extract the node attributes. Afterward, the graph convolution performs automatic feature extraction for nodes to classify the nodes as Trojan or benign. Our approach is automated and does not burden the designer with manual code review. It locates the Trojan signals with 99.6% accuracy, 93.1% $F$ 1-score, and a false-positive rate below 0.009%.


  • Hardware Trojan Detection Using Graph Neural Networks

    by Rozhin Yasaei, Luke Chen, Shih-Yuan Yu, Mohammad Abdullah Al Faruque

    The globalization of the integrated circuit (IC) supply chain has moved most of the design, fabrication, and testing process from a single trusted entity to various untrusted third-party entities around the world. The risk of using untrusted third-party intellectual property (3PIP) is the possibility for adversaries to insert malicious modifications known as hardware trojans (HTs). These HTs can compromise the integrity, deteriorate the performance, and deny the functionality of the intended design. Various HT detection methods have been proposed in the literature; however, many fall short due to their reliance on a golden reference circuit, a limited detection scope, the need for manual code review, or the inability to scale with large modern designs. We propose a novel golden reference-free HT detection method for both register transfer level (RTL) and gate-level netlists by leveraging graph neural networks (GNNs) to learn the behavior of the circuit through a data flow graph (DFG) representation of the hardware design. We evaluate our model on a custom dataset by expanding the Trusthub HT benchmarks (Shakya et al., 2017). The results demonstrate that our approach detects unknown HTs with 97% recall (true positive rate) very fast in 21.1 ms for RTL and 84% recall in 13.42 s for gate-level netlist.


  • Stealing Neural Network Structure Through Remote FPGA Side-Channel Analysis

    by Yicheng Zhang, Rozhin Yasaei, Hao Chen, Zhou Li, Mohammad Abdullah Al Faruque

    Deep Neural Network (DNN) models have been extensively developed by companies for a wide range of applications. The development of a customized DNN model with great performance requires costly investments, and its structure (layers and hyper-parameters) is considered intellectual property and holds immense value. However, in this paper, we found the model secret is vulnerable when a cloud-based FPGA accelerator executes it. We demonstrate an end-to-end attack based on remote power side-channel analysis and machine-learning-based secret inference against different DNN models. The evaluation result shows that an attacker can reconstruct the layer and hyper-parameter sequence at over 90% accuracy using our method, which can significantly reduce her model development workload. We believe the threat presented by our attack is tangible, and new defense mechanisms should be developed against this threat.


  • Open Access

    Technical Report for HW2VEC -- A Graph Learning Tool for Automating Hardware Security

    by Yasamin Moghaddas, Tommy Nguyen, Shih-Yuan Yu, Rozhin Yasaei, Mohammad Abdullah Al Faruque

    In this technical report, we present HW2VEC [11], an open-source graph learning tool for hardware security, and its implementation details (Figure 1). HW2VEC provides toolboxes for graph representation extraction in the form of Data Flow Graphs (DFGs) or Abstract Syntax Trees (ASTs) from hardware designs at RTL and GLN levels. Besides, HW2VEC also offers graph learning tools for representing hardware designs in vectors that preserve both structural features and behavioral features. To the best of our knowledge, HW2VEC is the first open-source research tool that supports applying graph learning methods to hardware designs in different abstraction levels for hardware security. We organize the remainder of this technical report as follows: Section 2 introduces the architecture of HW2VEC; Section 3 gives information about the use-case implementations; Section 4 provides the experimental results and demonstrates the performance of HW2VEC for two hardware security applications: HT detection and IP piracy detection; finally, Section 5 will conclude this report.


  • Brain-Inspired Golden Chip Free Hardware Trojan Detection

    by Sina Faezi, Rozhin Yasaei, Anomadarshi Barua, Mohammad Abdullah Al Faruque

    Since 2007, the use of side-channel measurements for detecting Hardware Trojan (HT) has been extensively studied. However, the majority of works either rely on a golden chip, or they rely on methods that are not robust against subtle acceptable changes that would occur over the life-cycle of an integrated circuit (IC). In this paper, we propose using a brain-inspired architecture called Hierarchical Temporal Memory (HTM) for HT detection. Similar to the human brain, our proposed solution is resilient against natural changes that might happen in the side-channel measurements while being able to accurately detect abnormal behavior of the chip when the HT gets triggered. We use a self-referencing method for HT detection, which eliminates the need for the golden chip. The effectiveness of our approach is evaluated using TrustHub benchmarks, which shows 92.20% detection accuracy on average.