按年被提到
20182022 · 2 次2026
视觉、语音与图像生成›生成对抗网络·arXiv:1810.00378 · cs.LG

Pseudo-Random Number Generation using Generative Adversarial Networks

Marcello De Bernardi, MHR Khouzani, Pasquale Malacaria · 2018
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2022-04-30 · 最近 2022-05-01
2不同的人
2活跃月份
2讨论串
31被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Pseudo-random number generators (PRNG) are a fundamental element of many security algorithms. We introduce a novel approach to their implementation, by proposing the use of generative adversarial networks (GAN) to train a neural network to behave as a PRNG. Furthermore, we showcase a number of interesting modifications to the standard GAN architecture. The most significant is partially concealing the output of the GAN's generator, and training the adversary to discover a mapping from the overt part to the concealed part. The generator therefore learns to produce values the adversary cannot predict, rather than to approximate an explicit reference distribution. We demonstrate that a GAN can effectively train even a small feed-forward fully connected neural network to produce pseudo-random number sequences with good statistical properties. At best, subjected to the NIST test suite, the trained generator passed around 99% of test instances and 98% of overall tests, outperforming a number of standard non-cryptographic PRNGs.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)
讨论串评论lgvld · 2022-05

“Seems crazy!.. Why? A NN couldn’t be used as a (valid) source of random, right? I thought a GAN actually need some random to start with... > The most significant is partially concealing the output of the GAN’s generator, and training the adversary to dis- cover a mapping from the overt part to the concealed part. The generator therefore learns to produc…”

Pseudo-Random Number Generation Using Generative Adversarial Networks (2018)原评论 ↗
讨论串评论airza · 2022-05

“It doesn't seem to be a very good idea to decide that since the discriminator cannot predict the output of the generator that prediction is impossible. I have been chipping away at improving ML prediction of non-CSPRNGs for the last few years and prediction is very sensitive to hyperparameter choice (thus far anyway). It seems easy to imagine a PRNG produ…”

Pseudo-Random Number Generation Using Generative Adversarial Networks (2018)原评论 ↗
讨论串评论Animats · 2022-05

“Hm. It's a way to make a good hash, not a good random number generator. A good hash is one where you put in nonrandom key values, maybe from a small set, and what comes out passes tests as random. For example, change one input bit and half the output bits should change. A good hasher coupled to a bad input looks like a random number generator, but it's n…”

Pseudo-Random Number Generation Using Generative Adversarial Networks (2018)原评论 ↗
被提交为 story · 2 次