arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.00609cs.LGcs.CR
收藏

攻击下模式分类器的安全性评估

Security Evaluation of Pattern Classifiers under Attack

University of Cagliari(卡利亚里大学)

Battista Biggio, Giorgio Fumera, Fabio Roli

摘要:

模式分类系统通常用于对抗性应用,如生物特征认证,网络入侵检测和垃圾邮件过滤,其中数据可以被人类故意操纵以破坏其操作。由于传统的设计方法没有考虑到这种对抗性的情况,模式分类系统可能会表现出漏洞,这些漏洞的利用可能会严重影响其性能,从而限制其实际效用。因此,将模式分类理论和设计方法扩展到对抗环境是一个新颖且非常相关的研究方向,尚未以系统的方式进行。在本文中,我们解决了一个主要的开放问题:评估在设计阶段的模式分类器的安全性,即潜在的攻击,他们可能会招致在操作过程中的性能下降。我们提出了一个框架,分类器的安全性,形式化和概括的主要思想在文献中提出的经验评估,并给出了它的使用在三个实际应用的例子。报告的结果表明,安全评估可以提供一个更完整的了解分类器的行为在对抗环境中,并导致更好的设计选择。

英文摘要:

Pattern classification systems are commonly used in adversarial applications, like biometric authentication, network intrusion detection, and spam filtering, in which data can be purposely manipulated by humans to undermine their operation. As this adversarial scenario is not taken into account by classical design methods, pattern classification systems may exhibit vulnerabilities, whose exploitation may severely affect their performance, and consequently limit their practical utility. Extending pattern classification theory and design methods to adversarial settings is thus a novel and very relevant research direction, which has not yet been pursued in a systematic way. In this paper, we address one of the main open issues: evaluating at design phase the security of pattern classifiers, namely, the performance degradation under potential attacks they may incur during operation. We propose a framework for empirical evaluation of classifier security that formalizes and generalizes the main ideas proposed in the literature, and give examples of its use in three real applications. Reported results show that security evaluation can provide a more complete understanding of the classifier's behavior in adversarial environments, and lead to better design choices.

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。

↑