Machine Learning based Modeling Attacks on a Configurable PUF

Kumar, Sharad; Niamat, Mohammed

doi:10.1109/naecon.2018.8556818

Cited by 17 publications

(9 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, such traditional methods are vulnerable to machine-learning attacks, such as logistic regression (LR) or NN attacks. [22] This claim is supported by the test results presented in Section IV.…”

Section: A Modulus Ring Oscillator (Mro)supporting

confidence: 55%

A Design Strategy to Improve Machine Learning Resiliency for Ring Oscillator Physically Unclonable Function

Jiang

Wang

2023

IEEE Access

View full text Add to dashboard Cite

Physically unclonable functions (PUFs) are hardware security primitives that utilize nonreproducible manufacturing variations to provide device-specific challenge-response pairs (CRPs). Such primitives are desirable for applications such as communication and intellectual property protection. PUFs have been gaining considerable interest from both the academic and industrial communities because of their simplicity and stability. However, many recent studies have exposed PUFs to machine-learning (ML) modeling attacks. To improve the resilience of a system to general ML attacks instead of a specific ML technique, a common solution is to improve the complexity of the system. Structures, such as XOR-PUFs, can significantly increase the nonlinearity of PUFs to provide resilience against ML attacks. However, an increase in complexity often results in an increase in area and/or a decrease in reliability. This study proposes a lightweight ring oscillator (RO)-based PUFs using an additional modulus process to improve ML resiliency. The idea was to increase the complexity of the RO-PUF without significant hardware overhead by applying a modulus process to the outcomes from the RO frequency counter. We also present a thorough investigation of the design space to balance ML resiliency and other performance metrics such as reliability, uniqueness, and uniformity.

show abstract

Section: A Modulus Ring Oscillator (Mro)supporting

confidence: 55%

A Design Strategy to Improve Machine Learning Resiliency for Ring Oscillator Physically Unclonable Function

Jiang

Wang

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Consequently, when presented with a set of unknown CRPs, the behavior of the PUF can be accurately predicted [26]. Successful machine learning attacks have been demonstrated using various methods, including Support Vector Machines (SVM), Artificial Neural Networks (ANN), and Multi-Layer Perceptron (MLP) [27][28][29].…”

Section: Attacks On Pufsmentioning

confidence: 99%

FLEX PUF: A Flexible Physical Unclonable Function Design Using Configurable Templates

Vega,

SLPSK,

Chatterjee

et al. 2023

Preprint

View full text Add to dashboard Cite

Field Programmable Gate Array (FPGA) has been seen as the intersection between cost and design time when compared to ASIC and DSP. Many of the security risks present in the supply chain apply to FPGA devices, and as such, there exists a need for FPGA-based security measures. Physically Unclonable Functions (PUFs) have shown to be a promising method for authenticating and validating devices. Current works have utilized FPGAs as a method for testing ASIC PUFs or do not utilize the FPGA architecture to the benefit of the PUF, limiting its potential application. In this work, we propose an FPGA-based PUF that takes advantage of the FPGA architecture to increase entropy. We propose a PUF that utilizes different design templates to switch out the method of entropy used to generate the PUF response. We also propose using the routing and placement constraints to further increase the entropy generated. By doing so, we can create a hybrid, strong memory-based PUF, where the placement, routing, and templates act as input challenges. To evaluate our PUF, we analyze the responses provided by a set of different templates to evaluate their uniqueness, robustness, and uniformity. Additionally, we evaluate the entropy provided by the templates and compare it to other templates and when mapped to different areas of the FPGA. We also evaluate the security benefits of our system and provide techniques for better leveraging the performance of our PUF.

show abstract

“…Models for bistable ring (BR) PUF [14] or twisted bistable ring (TBR) PUF [15] (both PUF based on feedback loops made of multiplexers and NOR gates which must achieve a stable state -the key-) have been reported. Typical solutions are based on support vector machines (SVM) [18]. Some authors have even analyzed different types of algorithms (SVM, genetic algorithms, etc.)…”

Section: Physical Unclonable Functions Modelingmentioning

confidence: 99%

Predictor-corrector models for lightweight massive machine-type communications in Industry 4.0

Bordel

Alcarria

Chung

et al. 2023

ICA

View full text Add to dashboard Cite

Future Industry 4.0 scenarios are characterized by seamless integration between computational and physical processes. To achieve this objective, dense platforms made of small sensing nodes and other resource constraint devices are ubiquitously deployed. All these devices have a limited number of computational resources, just enough to perform the simple operation they are in charge of. The remaining operations are delegated to powerful gateways that manage sensing nodes, but resources are never unlimited, and as more and more devices are deployed on Industry 4.0 platforms, gateways present more problems to handle massive machine-type communications. Although the problems are diverse, those related to security are especially critical. To enable sensing nodes to establish secure communications, several semiconductor companies are currently promoting a new generation of devices based on Physical Unclonable Functions, whose usage grows every year in many real industrial scenarios. Those hardware devices do not consume any computational resource but force the gateway to keep large key-value catalogues for each individual node. In this context, memory usage is not scalable and processing delays increase exponentially with each new node on the platform. In this paper, we address this challenge through predictor-corrector models, representing the key-value catalogues. Models are mathematically complex, but we argue that they consume less computational resources than current approaches. The lightweight models are based on complex functions managed as Laurent series, cubic spline interpolations, and Boolean functions also developed as series. Unknown parameters in these models are predicted, and eventually corrected to calculate the output value for each given key. The initial parameters are based on the Kane Yee formula. An experimental analysis and a performance evaluation are provided in the experimental section, showing that the proposed approach causes a significant reduction in the resource consumption.

show abstract

Machine Learning based Modeling Attacks on a Configurable PUF

Cited by 17 publications

References 5 publications

A Design Strategy to Improve Machine Learning Resiliency for Ring Oscillator Physically Unclonable Function

A Design Strategy to Improve Machine Learning Resiliency for Ring Oscillator Physically Unclonable Function

FLEX PUF: A Flexible Physical Unclonable Function Design Using Configurable Templates

Predictor-corrector models for lightweight massive machine-type communications in Industry 4.0

Contact Info

Product

Resources

About