arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.01621cs.CRcs.LG
收藏

ROOM:实时的约束下的对抗性机器学习攻击

ROOM: Adversarial Machine Learning Attacks Under Real-Time Constraints

IEMN-DOAE, UMR CNRS 8520 Polytechnic University Hauts-De-France(法国上法兰西理工大学 IEMN-DOAE, UMR CNRS 8520);George Mason University(乔治梅森大学);University of California Riverside(加州大学河滨分校)

Amira Guesmi, Khaled N. Khasawneh, Nael Abu-Ghazaleh, Ihsen Alouani

摘要:

深度学习的进步已经实现了广泛的有前途的应用。然而,这些系统容易受到对抗性机器学习(AML)攻击;对输入的恶意干扰可能导致它们错误分类。一些最先进的对抗攻击已经证明,它们可以可靠地欺骗分类器,使这些攻击成为一个重大的威胁。对抗攻击生成算法主要集中在创建成功的例子,同时控制噪声的大小和分布,使检测更加困难。这些攻击的基本假设是,对抗性噪声是离线生成的,因此执行时间是次要考虑因素。然而,最近,攻击者机会主义地在运行中生成对抗性示例的即时对抗攻击已被证明是可能的。本文提出了一个新的问题:如何在实时的【形】约束下产生对抗性噪声来支持这种实时的【形】对抗攻击?理解这个问题可以提高我们对这些攻击对实时的【形】系统构成的威胁的理解,并为未来的防御提供安全评估基准。因此,我们首先对对抗生成算法进行运行时分析。通用攻击离线产生通用攻击,没有在线开销,并且可以应用于任何输入;然而,由于其通用性,其成功率有限。相比之下,在线算法,工作在一个特定的输入,是计算昂贵的,使他们不适合在时间限制下的操作。因此,我们提出了ROOM,一种新的实时的【形】在线离线攻击构造模型,其中离线组件用于预热在线算法,使得在时间限制下生成非常成功的攻击成为可能。

英文摘要:

Advances in deep learning have enabled a wide range of promising applications. However, these systems are vulnerable to Adversarial Machine Learning (AML) attacks; adversarially crafted perturbations to their inputs could cause them to misclassify. Several state-of-the-art adversarial attacks have demonstrated that they can reliably fool classifiers making these attacks a significant threat. Adversarial attack generation algorithms focus primarily on creating successful examples while controlling the noise magnitude and distribution to make detection more difficult. The underlying assumption of these attacks is that the adversarial noise is generated offline, making their execution time a secondary consideration. However, recently, just-in-time adversarial attacks where an attacker opportunistically generates adversarial examples on the fly have been shown to be possible. This paper introduces a new problem: how do we generate adversarial noise under real-time constraints to support such real-time adversarial attacks? Understanding this problem improves our understanding of the threat these attacks pose to real-time systems and provides security evaluation benchmarks for future defenses. Therefore, we first conduct a run-time analysis of adversarial generation algorithms. Universal attacks produce a general attack offline, with no online overhead, and can be applied to any input; however, their success rate is limited because of their generality. In contrast, online algorithms, which work on a specific input, are computationally expensive, making them inappropriate for operation under time constraints. Thus, we propose ROOM, a novel Real-time Online-Offline attack construction Model where an offline component serves to warm up the online algorithm, making it possible to generate highly successful attacks under time constraints.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑