Modeling Attack Resistant PUFs Based on Adversarial Attack Against Machine Learning

Chen, Yu‐Sheng; Li, Katherine Shu-Min

doi:10.1109/jetcas.2021.3062413

Cited by 18 publications

(11 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the advancements in deep learning, PUF is vulnerable to modeling attacks [43,44]. Research has been going on to design a modeling attack resistant PUF [45]. Though many architectures were designed to resist the modeling attacks, the accuracy of such designs has always been over 70 % [44,45].…”

Section: Related Workmentioning

confidence: 99%

“…Research has been going on to design a modeling attack resistant PUF [45]. Though many architectures were designed to resist the modeling attacks, the accuracy of such designs has always been over 70 % [44,45]. With the high performance computing and developments in deep learning techniques, modeling attacks on PUF are becoming more aggressive and successful.…”

Section: Related Workmentioning

confidence: 99%

“…The researchers also noted that their framework performed better than a number of other robust PUFs that are currently ML-resistant. Wang et al [51] proposed a new ML-resistant robust PUF design. Their approach offers a way to combine inverted responses with regular ones, and that way ML algorithms are unable to generate a reliable model of the internal PUF.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

VXorPUF: A Vedic Principles - Based Hybrid XOR Arbiter PUF for Robust Security in IoMT

Mahmud¹,

Sadhu²,

Yanambaka³

et al. 2023

Preprint

View full text Add to dashboard Cite

The Internet of Medical Things (IoMT) is playing a pivotal role in the healthcare sector by allowing faster and more informed hospital care, personalized treatment, and medical solutions. A very effective and trustworthy solution for resource-constrained medical devices is provided by Physical Unclonable Functions (PUF) - based identity and authentication systems, however they are not yet entirely reliable. This paper proposes VXorPUF, a Vedic Principles - Based Hybrid XOR Arbiter PUF. Modeling attacks were performed on the proposed architecture and an accuracy of 49.80 % was achieved. Uniqueness, Reliability and Randomness were the figures of merit used to evaluate PUF.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

VXorPUF: A Vedic Principles - Based Hybrid XOR Arbiter PUF for Robust Security in IoMT

Mahmud¹,

Sadhu²,

Yanambaka³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…For the evaluation of performance in terms of reliability, uniqueness, bit-aliasing, uniformity, min-entropy and correlation [43,[46][47][48], our RO-PUF has been implemented on 25 Artix-7 FPGAs over a wide range of temperatures (0-85°C) with �5% variation in the core supply voltage (i.e. core voltage of 1V).…”

Section: Static (Long-term) Secret Key Generation Using Physical Uncl...mentioning

confidence: 99%

“…PicoPUF cell) in order to increase the ML attack. However, this type of attack during the learning phase needs a huge amount of PUF CRPs [48, 51]. Therefore, this ML‐based attack will not be effective against our proposed RO‐PUF design.…”

Section: Static and Ephemeral Private Key Generationsmentioning

confidence: 99%

Field Programmable Gate Array based elliptic curve Menezes‐Qu‐Vanstone key agreement protocol realization using Physical Unclonable Function and true random number generator primitives

Anandakumar

Hashmi

Sanadhya

2022

IET Circuits, Devices & Syst

View full text Add to dashboard Cite

The trust, authenticity and integrity of Internet-of-Things (IoT) systems are heavily reliant on Physical Unclonable Functions (PUFs) and True random number generators (TRNGs). The PUF and TRNG produce device intrinsic digital signatures and random binary sequences, which are used for cryptographic key generation, key agreement/exchange, device authentication, cloning prevention etc. This article reports an efficient Field Programmable Gate Array (FPGA)-based realization of elliptic curve Menezes-Qu-Vanstone (ECMQV)-authenticated key agreement protocol using PUF and TRNG with very competitive area-throughput trade-offs. The key agreement protocols, which establish a shared secret key between two IoT devices, make use of PUF and TRNG primitives for the long-and short-term secret keys generation while the elliptic curve is employed for public key generated from the corresponding secret key. The performance of the protocol is investigated on FPGAs. The authors' implementation of the ECMQV protocol takes 1.802 ms using 18852 slices on Artix-7 FPGA.

show abstract

Machine Learning for Secure Hardware Design

Mispan

Halak

2022

Machine Learning for Embedded System Security

View full text Add to dashboard Cite

Modeling Attack Resistant PUFs Based on Adversarial Attack Against Machine Learning

Cited by 18 publications

References 30 publications

VXorPUF: A Vedic Principles - Based Hybrid XOR Arbiter PUF for Robust Security in IoMT

VXorPUF: A Vedic Principles - Based Hybrid XOR Arbiter PUF for Robust Security in IoMT

Field Programmable Gate Array based elliptic curve Menezes‐Qu‐Vanstone key agreement protocol realization using Physical Unclonable Function and true random number generator primitives

Machine Learning for Secure Hardware Design

Contact Info

Product

Resources

About