Can Deep Learning Break a True Random Number Generator?

Yu, Yang; Moraitis, Michail; Dubrova, Elena

doi:10.1109/tcsii.2021.3066338

Cited by 12 publications

(9 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is reported that attacks on the RNGs are possible, both passively and actively, such as side-channel attacks (SCA) [ 74 ], fault injection attacks [ 75 , 76 , 77 ] and machine learning attacks [ 78 ]. With the rapidly advancing machine learning algorithms, new challenges are coming soon.…”

Section: Trngmentioning

confidence: 99%

“…Recently, a deep-learning-based SCA was developed to attack a TRNG, which was implemented on FPGA [ 78 ]. The original MURO-TRNG is presented in [ 73 ].…”

Section: Trngmentioning

confidence: 99%

“…If 200 extra flip-flops are added to the bitstream of the device under attack, an accuracy of close to 100% can be achieved, using the proposed bitstream modification process. Strictly speaking, the deep learning attack in [ 78 ] has not broken the core since the extra bitstream modification process is necessary. However, machine learning attacks remain a potential threat, and they have demonstrated some possible trends for successfully attacking a TRNG with the insertion of a hardware Trojan into the original design or chip.…”

Section: Trngmentioning

confidence: 99%

“… Power consumption of MURO-TRNG core [ 78 ]. ( a ) The origin design, ( b ) 200 extra flip-flops are added.…”

Section: Figurementioning

confidence: 99%

See 3 more Smart Citations

Entropy Sources Based on Silicon Chips: True Random Number Generator and Physical Unclonable Function

Cao

Liu

Lan

et al. 2022

Entropy

View full text Add to dashboard Cite

Entropy is a measure of uncertainty or randomness. It is the foundation for almost all cryptographic systems. True random number generators (TRNGs) and physical unclonable functions (PUFs) are the silicon primitives to respectively harvest dynamic and static entropy to generate random bit streams. In this survey paper, we present a systematic and comprehensive review of different state-of-the-art methods to harvest entropy from silicon-based devices, including the implementations, applications, and the security of the designs. Furthermore, we conclude the trends of the entropy source design to point out the current spots of entropy harvesting.

show abstract

Section: Trngmentioning

confidence: 99%

“…Recently, a deep-learning-based SCA was developed to attack a TRNG, which was implemented on FPGA [ 78 ]. The original MURO-TRNG is presented in [ 73 ].…”

Section: Trngmentioning

confidence: 99%

Section: Trngmentioning

confidence: 99%

“… Power consumption of MURO-TRNG core [ 78 ]. ( a ) The origin design, ( b ) 200 extra flip-flops are added.…”

Section: Figurementioning

confidence: 99%

See 2 more Smart Citations

Entropy Sources Based on Silicon Chips: True Random Number Generator and Physical Unclonable Function

Cao

Liu

Lan

et al. 2022

Entropy

View full text Add to dashboard Cite

show abstract

“…A major breakthrough is the utilization of machine learning in cryptanalysis of TRNGs, during which the attacker uses deep learning algorithms to analyze the circuit behavior and can infiltrate with relative ease. 11 The above discussed shortcomings of TRNGs make them unsuitable for cryptographic applications where electronic circuit based random number generation is not an option. For instance, sensor devices used in IoT frameworks are highly resource constrained in nature and are usually deployed in remote conditions where an attacker can easily gain access to the physical device and perform side channel analysis on the electronic circuit.…”

Section: Introductionmentioning

confidence: 99%

A resource efficient pseudo random number generator based on sawtooth maps for Internet of Things

Zia

McCartney

Scotney

et al. 2023

Security and Privacy

View full text Add to dashboard Cite

The strength of cryptographic keys rely on the random number generators (RNGs) to produce random seed values. Unfortunately there are not many RNGs options suitable for Internet of Things (IoTs) scenario, due to limited processing resources and bulk quantity of IoT data that needs to be secured. In this article, we studied sawtooth map which is a chaotic map. However, when implemented on a computer, the sawtooth map results on a non‐chaotic orbit due to the finite precision of computation. This can be avoided if we use the sawtooth map as the local map in a coupled map lattice (CML) system. We explore such coupled map systems for randomness through entropy and statistical analysis. Based on the results, we propose a lightweight hybrid pseudo random number generator (PRNG) based on sawtooth based CML system and SPONGENT hashing. The proposed PRNG is thoroughly tested against statistical attacks, entropy analysis, key space analysis and compared with existing state of the art solutions. The results provide evidence that the proposed PRNG produces random numbers that could produce sufficiently strong cryptographic keys for resource constrained IoT devices.

show abstract

QSKCG: Quantum‐based secure key communication and key generation scheme for outsourced data in cloud

Adouth,

Rajagopal

2024

Concurrency and Computation

View full text Add to dashboard Cite

In the era of digital proliferation, individuals opt for cloud servers to store their data due to the diverse advantages they offer. However, entrusting data to cloud servers relinquishes users' control, potentially compromising data confidentiality and integrity. Traditional auditing methods designed to ensure data integrity in cloud servers typically depend on Trusted Third Party Auditors. Yet, many of these existing auditing approaches grapple with intricate certificate management and key escrow issues. Furthermore, the imminent threat of powerful quantum computers poses a risk of swiftly compromising these methods in polynomial time. To overcome these challenges, this paper introduces a Quantum‐based Secure Key Communication and Key Generation Scheme QSKCG for Outsourced Data in the Cloud. Leveraging Elliptic Curve Cryptography, the BB84 secure communication protocol, certificateless signature, and blockchain network, the proposed scheme is demonstrated through security analysis, affirming its robustness and high efficiency. Additionally, performance analysis underscores the practicality of the proposed scheme in achieving post‐quantum security in cloud storage.

show abstract

Can Deep Learning Break a True Random Number Generator?

Cited by 12 publications

References 28 publications

Entropy Sources Based on Silicon Chips: True Random Number Generator and Physical Unclonable Function

Entropy Sources Based on Silicon Chips: True Random Number Generator and Physical Unclonable Function

A resource efficient pseudo random number generator based on sawtooth maps for Internet of Things

QSKCG: Quantum‐based secure key communication and key generation scheme for outsourced data in cloud

Contact Info

Product

Resources

About