David Selasi Koblah
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
David Selasi Koblah has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Domenic Forte
University of Florida, Gainesville, FL, USA
6 shared publications - Damon L. Woodard
University of Florida
4 shared publications - Fatemeh Ganji
Worcester Polytechnic Institute, Worcester, MA, USA
3 shared publications - Olivia P. Dizon-Paradis
Florida Institute for National Security, Electrical and Computer Engineering Department, University of Florida
3 shared publications Damon L. Woodard
Florida Institute for National Security, Electrical and Computer Engineering Department, University of Florida
2 shared publicationsDomenic Forte
Florida Institute for National Security, Electrical and Computer Engineering Department, University of Florida
2 shared publications
Latest Publications
- Open Access
Designing with Deception: ML- and Covert Gate-Enhanced Camouflaging to Thwart IC Reverse Engineering
Integrated circuits (ICs) are essential to modern electronic systems, yet they face significant risks from physical reverse engineering (RE) attacks that compromise intellectual property (IP) and overall system security. While IC camouflage techniques have emerged to mitigate these risks, existing approaches largely focus on localized gate modifications, neglecting comprehensive deception strategies. To address this gap, we present a machine learning (ML)-driven methodology that integrates cryptic and mimetic cyber deception principles to enhance IC security against RE. Our approach leverages a novel And-Inverter Graph Variational Autoencoder (AIG-VAE) to encode circuit representations, enabling dual-layered camouflage through functional preservation and appearance mimicry. By introducing new variants of covert gates -- Fake Inverters, Fake Buffers, and Universal Transmitters -- our methodology achieves robust protection by obscuring circuit functionality while presenting misleading appearances. Experimental results demonstrate the effectiveness of our strategy in maintaining circuit functionality while achieving high camouflage and similarity scores with minimal structural overhead. Additionally, we validate the robustness of our method against advanced artificial intelligence (AI)-enhanced RE attacks, highlighting its practical applicability in securing IC designs. By bridging the gap in mimetic deception for hardware security, our work sets a new standard for IC camouflage, advancing the application of cyber deception principles to protect critical systems from adversarial threats.
Open AccessDesigning with Deception: ML- and Covert Gate-Enhanced Camouflaging to Thwart IC Reverse Engineering
Integrated circuits (ICs) are essential to modern electronic systems, yet they face significant risks from physical reverse engineering (RE) attacks that compromise intellectual property (IP) and overall system security. While IC camouflage techniques have emerged to mitigate these risks, existing approaches largely focus on localized gate modifications, neglecting comprehensive deception strategies. To address this gap, we present a machine learning (ML)-driven methodology that integrates cryptic and mimetic cyber deception principles to enhance IC security against RE. Our approach leverages a novel And-Inverter Graph Variational Autoencoder (AIG-VAE) to encode circuit representations, enabling dual-layered camouflage through functional preservation and appearance mimicry. By introducing new variants of covert gates -- Fake Inverters, Fake Buffers, and Universal Transmitters -- our methodology achieves robust protection by obscuring circuit functionality while presenting misleading appearances. Experimental results demonstrate the effectiveness of our strategy in maintaining circuit functionality while achieving high camouflage and similarity scores with minimal structural overhead. Additionally, we validate the robustness of our method against advanced artificial intelligence (AI)-enhanced RE attacks, highlighting its practical applicability in securing IC designs. By bridging the gap in mimetic deception for hardware security, our work sets a new standard for IC camouflage, advancing the application of cyber deception principles to protect critical systems from adversarial threats.
- Open Access
- 6 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
IC SEM Reverse Engineering Tutorial using Artificial Intelligence
In this tutorial, we will leverage artificial intelligence (AI) techniques to facilitate the reverse engineering of an integrated circuit based on scanning electron microspcopy, contributing to hardware assurance. This work encompasses various subjects, including image processing, computer vision, and machine learning, providing a comprehensive learning experience in these specialized domains. We encourage you to actively participate in this tutorial to execute your own project. The skills and knowledge acquired in this activity can bolster your resume, enhancing your prospects when seeking employment, pursuing further education, or advancing in your current professional role.
- 6 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessIC SEM Reverse Engineering Tutorial using Artificial Intelligence
In this tutorial, we will leverage artificial intelligence (AI) techniques to facilitate the reverse engineering of an integrated circuit based on scanning electron microspcopy, contributing to hardware assurance. This work encompasses various subjects, including image processing, computer vision, and machine learning, providing a comprehensive learning experience in these specialized domains. We encourage you to actively participate in this tutorial to execute your own project. The skills and knowledge acquired in this activity can bolster your resume, enhancing your prospects when seeking employment, pursuing further education, or advancing in your current professional role.
- 9 May 2025
- Published by Springer Nature
- p. 282-292
eXpLogic: Explaining Logic Types and Patterns in DiffLogic Networks
- 9 May 2025
- Published by Springer Nature
- p. 282-292
eXpLogic: Explaining Logic Types and Patterns in DiffLogic Networks
- Open Access
eXpLogic: Explaining Logic Types and Patterns in DiffLogic Networks
Constraining deep neural networks (DNNs) to learn individual logic types per node, as performed using the DiffLogic network architecture, opens the door to model-specific explanation techniques that quell the complexity inherent to DNNs. Inspired by principles of circuit analysis from computer engineering, this work presents an algorithm (eXpLogic) for producing saliency maps which explain input patterns that activate certain functions. The eXpLogic explanations: (1) show the exact set of inputs responsible for a decision, which helps interpret false negative and false positive predictions, (2) highlight common input patterns that activate certain outputs, and (3) help reduce the network size to improve class-specific inference. To evaluate the eXpLogic saliency map, we introduce a metric that quantifies how much an input changes before switching a model's class prediction (the SwitchDist) and use this metric to compare eXpLogic against the Vanilla Gradients (VG) and Integrated Gradient (IG) methods. Generally, we show that eXpLogic saliency maps are better at predicting which inputs will change the class score. These maps help reduce the network size and inference times by 87\% and 8\%, respectively, while having a limited impact (-3.8\%) on class-specific predictions. The broader value of this work to machine learning is in demonstrating how certain DNN architectures promote explainability, which is relevant to healthcare, defense, and law.
Open AccesseXpLogic: Explaining Logic Types and Patterns in DiffLogic Networks
Constraining deep neural networks (DNNs) to learn individual logic types per node, as performed using the DiffLogic network architecture, opens the door to model-specific explanation techniques that quell the complexity inherent to DNNs. Inspired by principles of circuit analysis from computer engineering, this work presents an algorithm (eXpLogic) for producing saliency maps which explain input patterns that activate certain functions. The eXpLogic explanations: (1) show the exact set of inputs responsible for a decision, which helps interpret false negative and false positive predictions, (2) highlight common input patterns that activate certain outputs, and (3) help reduce the network size to improve class-specific inference. To evaluate the eXpLogic saliency map, we introduce a metric that quantifies how much an input changes before switching a model's class prediction (the SwitchDist) and use this metric to compare eXpLogic against the Vanilla Gradients (VG) and Integrated Gradient (IG) methods. Generally, we show that eXpLogic saliency maps are better at predicting which inputs will change the class score. These maps help reduce the network size and inference times by 87\% and 8\%, respectively, while having a limited impact (-3.8\%) on class-specific predictions. The broader value of this work to machine learning is in demonstrating how certain DNN architectures promote explainability, which is relevant to healthcare, defense, and law.
- Open Access
- 5 September 2024
- Published by Universitatsbibliothek der Ruhr-Universitat Bochum in IACR Transactions on Cryptographic Hardware and Embedded Systems
- Vol. 2024 (4) , 569-609
Bake It Till You Make It
Masking has become one of the most effective approaches for securing hardware designs against side-channel attacks. Regardless of the effort put into correctly implementing masking schemes on a field-programmable gate array (FPGA), leakage can be unexpectedly observed. This is due to the fact that the assumption underlying all masked designs, i.e., the leakages of different shares are independent of each other, may no longer hold in practice. In this regard, extreme temperatures have been shown to be an important factor in inducing leakage, even in correctlymasked designs. This has previously been verified using an external heat generator (i.e., a climate chamber). In this paper, we examine whether the leakage can be induced using the circuit components themselves without making any changes to the design. Specifically, we target masked neural networks (NNs) in FPGAs, one of the main building blocks of which is block random access memory (BRAM). In this respect, thanks to the inherent characteristics of NNs, our novel internal heat generators leverage solely the memories devoted to storing the user’s input, especially when frequently writing alternating patterns into BRAMs. The possibility of observing first-order leakage is evaluated by considering one of the most recent and successful first-order secure masked NNs, namely ModuloNET. ModuloNET is specifically designed for FPGAs, where BRAMs are used to store inputs and intermediate computations. Our experimental results demonstrate that undesirable first-order leakage can be observed and exploited by increasing the temperature when an alternating input is applied to the masked NN. To give a better understanding of the impact of extreme heat, we further perform a similar test on the design using an external heat generator, where a similar conclusion can be drawn.
- 5 September 2024
- Published by Universitatsbibliothek der Ruhr-Universitat Bochum in IACR Transactions on Cryptographic Hardware and Embedded Systems
- Vol. 2024 (4) , 569-609
Open AccessBake It Till You Make It
Masking has become one of the most effective approaches for securing hardware designs against side-channel attacks. Regardless of the effort put into correctly implementing masking schemes on a field-programmable gate array (FPGA), leakage can be unexpectedly observed. This is due to the fact that the assumption underlying all masked designs, i.e., the leakages of different shares are independent of each other, may no longer hold in practice. In this regard, extreme temperatures have been shown to be an important factor in inducing leakage, even in correctlymasked designs. This has previously been verified using an external heat generator (i.e., a climate chamber). In this paper, we examine whether the leakage can be induced using the circuit components themselves without making any changes to the design. Specifically, we target masked neural networks (NNs) in FPGAs, one of the main building blocks of which is block random access memory (BRAM). In this respect, thanks to the inherent characteristics of NNs, our novel internal heat generators leverage solely the memories devoted to storing the user’s input, especially when frequently writing alternating patterns into BRAMs. The possibility of observing first-order leakage is evaluated by considering one of the most recent and successful first-order secure masked NNs, namely ModuloNET. ModuloNET is specifically designed for FPGAs, where BRAMs are used to store inputs and intermediate computations. Our experimental results demonstrate that undesirable first-order leakage can be observed and exploited by increasing the temperature when an alternating input is applied to the masked NN. To give a better understanding of the impact of extreme heat, we further perform a similar test on the design using an external heat generator, where a similar conclusion can be drawn.
- Open Access
- 11 October 2023
- Published by Association for Computing Machinery (ACM) in ACM Journal on Emerging Technologies in Computing Systems
- Vol. 19 (4) , 1-20
A Fast Object Detection-Based Framework for Via Modeling on PCB X-Ray CT Images
For successful printed circuit board (PCB) reverse engineering (RE), the resulting device must retain the physical characteristics and functionality of the original. Although the applications of RE are within the discretion of the executing party, establishing a viable, non-destructive framework for analysis is vital for any stakeholder in the PCB industry. A widely regarded approach in PCB RE uses non-destructive x-ray computed tomography (CT) to produce three-dimensional volumes with several slices of data corresponding to multi-layered PCBs. However, the noise sources specific to x-ray CT and variability from designers hampers the thorough acquisition of features necessary for successful RE. This article investigates a deep learning approach as a successor to the current state-of-the-art for detecting vias on PCB x-ray CT images; vias are a key building block of PCB designs. During RE, vias offer an understanding of the PCB’s electrical connections across multiple layers. Our method is an improvement on an earlier iteration which demonstrates significantly faster runtime with quality of results comparable to or better than the current state-of-the-art, unsupervised iterative Hough-based method. Compared with the Hough-based method, the current framework is 4.5 times faster for the discrete image scenario and 24.1 times faster for the volumetric image scenario. The upgrades to the prior deep learning version include faster feature-based detection for real-world usability and adaptive post-processing methods to improve the quality of detections.
- 11 October 2023
- Published by Association for Computing Machinery (ACM) in ACM Journal on Emerging Technologies in Computing Systems
- Vol. 19 (4) , 1-20
Open AccessA Fast Object Detection-Based Framework for Via Modeling on PCB X-Ray CT Images
For successful printed circuit board (PCB) reverse engineering (RE), the resulting device must retain the physical characteristics and functionality of the original. Although the applications of RE are within the discretion of the executing party, establishing a viable, non-destructive framework for analysis is vital for any stakeholder in the PCB industry. A widely regarded approach in PCB RE uses non-destructive x-ray computed tomography (CT) to produce three-dimensional volumes with several slices of data corresponding to multi-layered PCBs. However, the noise sources specific to x-ray CT and variability from designers hampers the thorough acquisition of features necessary for successful RE. This article investigates a deep learning approach as a successor to the current state-of-the-art for detecting vias on PCB x-ray CT images; vias are a key building block of PCB designs. During RE, vias offer an understanding of the PCB’s electrical connections across multiple layers. Our method is an improvement on an earlier iteration which demonstrates significantly faster runtime with quality of results comparable to or better than the current state-of-the-art, unsupervised iterative Hough-based method. Compared with the Hough-based method, the current framework is 4.5 times faster for the discrete image scenario and 24.1 times faster for the volumetric image scenario. The upgrades to the prior deep learning version include faster feature-based detection for real-world usability and adaptive post-processing methods to improve the quality of detections.
- 24 April 2023
- Published by Springer Nature in Journal of Hardware and Systems Security
- Vol. 7 (2-3) , 25-43
A Comprehensive Taxonomy of Visual Printed Circuit Board Defects
- 24 April 2023
- Published by Springer Nature in Journal of Hardware and Systems Security
- Vol. 7 (2-3) , 25-43
A Comprehensive Taxonomy of Visual Printed Circuit Board Defects
- Open Access
- 6 March 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 28 (2) , 1-57
A Survey and Perspective on Artificial Intelligence for Security-Aware Electronic Design Automation
Artificial intelligence (AI) and machine learning (ML) techniques have been increasingly used in several fields to improve performance and the level of automation. In recent years, this use has exponentially increased due to the advancement of high-performance computing and the ever increasing size of data. One of such fields is that of hardware design—specifically the design of digital and analog integrated circuits, where AI/ ML techniques have been extensively used to address ever-increasing design complexity, aggressive time to market, and the growing number of ubiquitous interconnected devices. However, the security concerns and issues related to integrated circuit design have been highly overlooked. In this article, we summarize the state-of-the-art in AI/ML for circuit design/optimization, security and engineering challenges, research in security-aware computer-aided design/electronic design automation, and future research directions and needs for using AI/ML for security-aware circuit design.
- 6 March 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Design Automation of Electronic Systems
- Vol. 28 (2) , 1-57
Open AccessA Survey and Perspective on Artificial Intelligence for Security-Aware Electronic Design Automation
Artificial intelligence (AI) and machine learning (ML) techniques have been increasingly used in several fields to improve performance and the level of automation. In recent years, this use has exponentially increased due to the advancement of high-performance computing and the ever increasing size of data. One of such fields is that of hardware design—specifically the design of digital and analog integrated circuits, where AI/ ML techniques have been extensively used to address ever-increasing design complexity, aggressive time to market, and the growing number of ubiquitous interconnected devices. However, the security concerns and issues related to integrated circuit design have been highly overlooked. In this article, we summarize the state-of-the-art in AI/ML for circuit design/optimization, security and engineering challenges, research in security-aware computer-aided design/electronic design automation, and future research directions and needs for using AI/ML for security-aware circuit design.