paper-with-me

Papers

Adversarial Examples from Cryptographic Pseudo-Random Generators

2018-11-15 · Sébastien Bubeck, Yin Tat Lee, Eric Price, Ilya Razenshteyn

In our recent work (Bubeck, Price, Razenshteyn, arXiv:1805.10204) we argued that adversarial examples in machine learning might be due to an inherent computational hardness of the problem. More precisely, we constructed a binary classification task for which (i) a robust classifier exists; yet no non-trivial accuracy can be obtained with an efficient algorithm in (ii) the statistical query model. In the present paper we significantly strengthen both (i) and (ii): we now construct a task which admits (i') a maximally robust classifier (that is it can tolerate perturbations of size comparable to the size of the examples themselves); and moreover we prove computational hardness of learning this task under (ii') a standard cryptographic assumption.

📄 PDF Abstract BibTeX arXiv:1811.06418

Code (0)

등록된 구현이 없습니다.

Tasks

Binary ClassificationGeneral Classification

Similar Papers 제목 키워드 기반

Pseudo-Random Number Generation using Generative Adversarial Networks

2018-09-30 · Marcello De Bernardi, MHR Khouzani, Pasquale Malacaria

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 …

Minimax Optimality (Probably) Doesn't Imply Distribution Learning for GANs

2022-01-18 · ICLR 2022 4 · Sitan Chen, Jerry Li, Yuanzhi Li, Raghu Meka

Arguably the most fundamental question in the theory of generative adversarial networks (GANs) is to understand to what extent GANs can actually learn the underlying distribution. Theoretical and empirical evidence sugge…

Combining Generators of Adversarial Malware Examples to Increase Evasion Rate

2023-04-14 · Matouš Kozák, Martin Jureček

Antivirus developers are increasingly embracing machine learning as a key component of malware defense. While machine learning achieves cutting-edge outcomes in many fields, it also has weaknesses that are exploited by s…

Adversarial Attack

Machine Learning Cryptanalysis of a Quantum Random Number Generator

2019-05-07 · Nhan Duy Truong, Jing Yan Haw, Syed Muhamad Assad, Ping Koy Lam 외

Random number generators (RNGs) that are crucial for cryptographic applications have been the subject of adversarial attacks. These attacks exploit environmental information to predict generated random numbers that are s…

BenchmarkingBIG-bench Machine LearningCryptanalysis

EIM-TRNG: Obfuscating Deep Neural Network Weights with Encoding-in-Memory True Random Number Generator via RowHammer

2025-07-03 · Ranyang Zhou, Abeer Matar A. Almalky, Gamana Aragonda, Sabbir Ahmed 외 arxiv

True Random Number Generators (TRNGs) play a fundamental role in hardware security, cryptographic systems, and data protection. In the context of Deep NeuralNetworks (DNNs), safeguarding model parameters, particularly we…