Pseudo Random Number Generation Using LSTMs and Irrational Numbers

Jeong, Young-Seob; Oh, Kyo-Joong; Cho, Chung-Ki; Choi, Ho-Jin

doi:10.1109/bigcomp.2018.00091

Cited by 22 publications

(10 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nearly 95 % of NIST tests can be consistently passed by the trained generator, indicating that the adversarial procedure is extremely effective in training the network to act as a PRNG. Findings are comparable to those of Tirdad and Sadeghian [50], and Jeong et al [21], outperforming a range of regular PRNGs. This proposed cluster synchronization has several advantages that are as follows:…”

Section: Related Worksupporting

confidence: 78%

“…Several efforts are being made with neural networks to produce PRNG sequences by Desai et al [10], Desai et al [9], Tirdad and Sadeghian [50], Jeong et al [21]. Tirdad and Sadeghian [50] and Jeong et al [21], have described the most effective methods. The previous was using Hopfield neural networks to avoid convergence and promote dynamic behavior, whereas the latter used a random data sampletrained LSTM to acquire indices in the pi digits.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Generative adversarial network guided mutual learning based synchronization of cluster of neural networks

Sarkar

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

Neural synchronization is a technique for establishing the cryptographic key exchange protocol over a public channel. Two neural networks receive common inputs and exchange their outputs. In some steps, it leads to full synchronization by setting the discrete weights according to the specific rule of learning. This synchronized weight is used as a common secret session key. But there are seldom research is done to investigate the synchronization of a cluster of neural networks. In this paper, a Generative Adversarial Network (GAN)-based synchronization of a cluster of neural networks with three hidden layers is proposed for the development of the public-key exchange protocol. This paper highlights a variety of interesting improvements to traditional GAN architecture. Here GAN is used for Pseudo-Random Number Generators (PRNG) for neural synchronization. Each neural network is considered as a node of a binary tree framework. When both i-th and j-th nodes of the binary tree are synchronized then one of these two nodes is elected as a leader. Now, this leader node will synchronize with the leader of the other branch. After completion of this process synchronized weight becomes the session key for the whole cluster. This proposed technique has several advantages like (1) There is no need to synchronize one neural network to every other in the cluster instead of that entire cluster can be able to share the same secret key by synchronizing between the elected leader nodes with only logarithmic synchronization steps. (2) This proposed technology provides GAN-based PRNG which is very sensitive to the initial seed value. (3) Three hidden layers leads to the complex internal architecture of the Tree Parity Machine (TPM). So, it will be difficult for the attacker to guess the internal architecture. (4) An increase in the weight range of the neural network increases the complexity of a successful attack exponentially but the effort to build the neural key decreases over the polynomial time. (5) The proposed technique also offers synchronization and authentication steps in parallel. It is difficult for the attacker to distinguish between synchronization and authentication steps. This proposed technique has been passed through different parametric tests. Simulations of the process show effectiveness in terms of cited results in the paper.

show abstract

Section: Related Worksupporting

confidence: 78%

Section: Related Workmentioning

confidence: 99%

Generative adversarial network guided mutual learning based synchronization of cluster of neural networks

Sarkar

2021

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…Some of them are as follows: 1. PRNG: It stands for Pseudo-random number generators (PRNGs), are predefined procedures that are capable to deliberately generate long numbers with excellent random properties but sometimes the sequence may repeat [5]. The random numbers generated by such algorithms is generally determined by a fixed number called seed [6].…”

Section: Related Workmentioning

confidence: 99%

An Input Based Random Number Generator

Yadav,

Kumar

2019

IJRTE

View full text Add to dashboard Cite

The this research article, a neoteric technique is introduced to generate four digit random number for authenticating a user as well as increasing the security of wireless and wired networks by using input based random number generator. An input based random number generator uses number conversion technique and some logical operations. Though the degree of randomness of generated number will not become very high but this hypothesis will increase the security in different areas of computer and sensor network.

show abstract

“…Unfortunately, as compared to a TRNG, a regular PRNG is quite vulnerable to machine learning (ML) attacks since ML is able to model algorithms [3]. For example, long-short term memory (LSTM) [4] is a kind of advanced ML technique that was demonstrated to be efficient in cracking a regular PRNG. The primary reason is that a hardware-implemented PRNG belongs to a sequential logic circuit while LSTM is pretty efficient in modelling sequential logic circuits.…”

mentioning

confidence: 99%

“…Security robustness against regular LSTM attacks: Since a hardware-implemented regular PRNG is a sequential logic circuit that contains at least one feedback loop, LSTM algorithm [4] can be explored to model the regular PRNG. Fig.…”

mentioning

confidence: 99%

Machine learning‐resistant pseudo‐random number generator

Wen¹,

Yu²

2019

Electron. lett.

View full text Add to dashboard Cite

Conventional pseudo-random number generator (PRNG) is vulnerable to machine learning (ML) attacks since algorithms are used to generate the random number. Physical unclonable function (PUF) is a kind of hardware security primitive that can also be cracked by ML attacks. However, the main security difference between a regular PRNG and a PUF is that training the output data of a regular PRNG is sufficient to break the PRNG while the challenge-to-response pairs of a PUF must be available for a successful training. In order to design a ML-resistant PRNG, in this Letter, the output data of a regular PRNG is fed into a PUF to generate the encrypted data first. Then the encrypted data is added to the output data of the other regular PRNG to create the output data for the ML-resistant PRNG. Since the input challenge of the PUF is concealed, the adversary is unable to model the PUF with ML techniques. The result shows that the training accuracy of a single output bit of the ML-resistant PRNG is only about 52.6% even if 200,000 data are sampled for training. In contrast, only 50,000 data are adequate to break a regular PRNG if ML attacks are executed.

show abstract

Pseudo Random Number Generation Using LSTMs and Irrational Numbers

Cited by 22 publications

References 6 publications

Generative adversarial network guided mutual learning based synchronization of cluster of neural networks

Generative adversarial network guided mutual learning based synchronization of cluster of neural networks

An Input Based Random Number Generator

Machine learning‐resistant pseudo‐random number generator

Contact Info

Product

Resources

About