Skip to Main Content
 

Global Search Box

 
 
 

ETD Abstract Container

Abstract Header

Hardware Security Design, and Vulnerability Analysis of FPGA based PUFs to Machine Learning and Swarm Intelligence based ANN Algorithm Attacks

Oun, Ahmed
http://orcid.org/0000-0001-6069-9261
http://rave.ohiolink.edu/etdc/view?acc_num=toledo1651595714554771

Abstract Details

2022, Doctor of Philosophy, University of Toledo, Engineering.
With the increasing trend of outsourcing the fabrication process of Integrated Circuits (ICs) to foreign foundries, hardware security threats have significantly increased. Of particular concern is the infiltration of the IC supply chain with compromised and counterfeit chips by untrusted and dubious foundries. In recent years, the use of programmable devices such as Field Programmable Gate Arrays (FPGAs) has rapidly increased. The increased deployment of these devices in mission-critical computing systems such as communication networks, smart grids, defense equipment, and internet of things; has led hackers to continually devise new techniques to breach the security of these devices. Of serious concern is the implantation of a spurious circuitry, known as a Trojan, to steal or degrade the function of the chip. These tampered chips can subsequently act as ‘spy chips’ for collecting confidential data by adversaries and hackers. To counter such attacks, a chip designer can embed additional security layers in these devices using Physical Unclonable Functions (PUFs). Although PUFs are supposed to be unclonable and unbreakable, researchers have found that they are vulnerable to Machine Learning (ML) attacks. From a subset of challenge-response pairs (CRPs), the remaining CRPs can be effectively predicted using different machine learning algorithms. This research presents a comprehensive vulnerability analysis of different FPGA based PUFs to various Swarm Intelligence (SI) based ANN Algorithms (SI) attacks; namely, Dragonfly Algorithm (DA), Gravitational Search Algorithm (GSA), Cuckoo Search Algorithm (CS), Particle Swarm Optimization (PSO), and the Grey Wolf Optimizer (GWO) algorithms. These algorithms are used to build Artificial Neural Network models to analyze the vulnerability of the different PUFs for modeling attacks. The training algorithms adjust the weights and biases of the ANN to obtain the highest response prediction accuracy by finding their optimum set. To the best of our knowledge, swarm intelligence-based algorithms have not been used in studying the vulnerability of PUFs to ANN-based attacks. The results show that the swarm intelligence algorithms produce better response prediction accuracies results (71.1% - 99.3%) when compared to other well-known ML algorithms. Amongst the various SI and ML algorithms, the GWO algorithm performs the best in predicting the CRPs. This research further focuses on using different machine learning classifiers attacks, namely: Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), K-Nearest Neighbor (KNN), kernel Support Vector (Kernel SVM), Naive Bayes Classifier (NB). Different Artificial Neural Networks (ANN) based models to study the vulnerability of PUFs are used by modeling the challenge-response pairs. The ANN models are implemented using four different optimization techniques; namely: Root Mean Square Propagation (RMSprop), Adaptive delta (Adadelta) learning rate method for gradient descent, Adaptive Moment Estimation (Adam), and Nesterov-accelerated Adaptive Moment Estimation (Nadam). The challenge-response data obtained from different PUFs are trained using various modeling algorithms. The results show that the ANN-based algorithms produce better response prediction accuracies results (68.0% - 94.1%) when compared with other ML algorithms. Two different novel XOR-ROPUFs capable of thwarting various machine learning modeling attacks, and enhancing the security of the PUFs, are also designed. The proposed designs are implemented on Xilinx Artix-7 FPGAs. These PUFs generate an ‘n’ bit response for an ‘n’ bit challenge (n x n); the new response is an ‘n’ bit vector so that the prediction accuracy is calculated based on predicting the number of bit strings (n x n) for different challenges. The new PUF structures drastically reduces the prediction accuracy of CRPs to 24.1%. For the remaining part of this research work, an authentication scheme is proposed for the security of IoT systems using a lightweight XOR-ROPUF. The proposed management scheme carries out the authentication between the verification authority, the authentication server, and the IoT devices to ensure data congeniality and integrity. The proposed XOR-ROPUF based scheme implements a low-cost device authentication solution for identifying the trusted hardware, securing communication among the devices using a lightweight system, and reducing the risk of authentication vulnerability.
Mohammed Niamat, PhD (Committee Chair)
Richard Molyet, PhD (Committee Member)
Weiqing Sun, PhD (Committee Member)
Ahmad Javaid, PhD (Committee Member)
Junghwan Kim, PhD (Committee Member)
151 p.
Artificial Intelligence; Computer Engineering; Electrical Engineering; Systems Design
Hardware security, FPGA, PUF, artificial neural network, swarm intelligence, machine learning attacks, Authentication, Internet of Things.

Recommended Citations

Citations

  • Oun, A. (2022). Hardware Security Design, and Vulnerability Analysis of FPGA based PUFs to Machine Learning and Swarm Intelligence based ANN Algorithm Attacks [Doctoral dissertation, University of Toledo]. OhioLINK Electronic Theses and Dissertations Center. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1651595714554771

    APA Style (7th edition)

  • Oun, Ahmed. Hardware Security Design, and Vulnerability Analysis of FPGA based PUFs to Machine Learning and Swarm Intelligence based ANN Algorithm Attacks. 2022. University of Toledo, Doctoral dissertation. OhioLINK Electronic Theses and Dissertations Center, http://rave.ohiolink.edu/etdc/view?acc_num=toledo1651595714554771.

    MLA Style (8th edition)

  • Oun, Ahmed. "Hardware Security Design, and Vulnerability Analysis of FPGA based PUFs to Machine Learning and Swarm Intelligence based ANN Algorithm Attacks." Doctoral dissertation, University of Toledo, 2022. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1651595714554771

    Chicago Manual of Style (17th edition)

toledo1651595714554771
515
© 2022, all rights reserved.
This open access ETD is published by University of Toledo and OhioLINK.