arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.09465cs.CRcs.LG
收藏

攻击、防御和工具:促进健壮AI/ML系统的框架

Attacks, Defenses, And Tools: A Framework To Facilitate Robust AI/ML Systems

Rochester Institute of Technology(罗切斯特理工学院)

Mohamad Fazelnia, Igor Khokhlov, Mehdi Mirakhorli

摘要:

软件系统越来越依赖于人工智能(AI)和机器学习(ML)组件。人工智能技术在各个应用领域的新兴流行吸引了恶意行为者和对手。因此,支持AI的软件系统的开发人员需要考虑这些系统可能容易受到的各种新型网络攻击和漏洞。本文提出了一个框架来描述与AI系统相关的攻击和弱点,并提供缓解技术和防御策略。该框架旨在支持支持软件设计人员采取积极措施开发支持AI的软件,了解此类系统的攻击面,并开发能够抵御与ML相关的各种新兴攻击的产品。开发的框架涵盖了广泛的攻击,缓解技术,防御和攻击工具。在本文中,我们展示了框架架构及其主要组件,描述了它们的属性,并讨论了这项研究的长期目标。

英文摘要:

Software systems are increasingly relying on Artificial Intelligence (AI) and Machine Learning (ML) components. The emerging popularity of AI techniques in various application domains attracts malicious actors and adversaries. Therefore, the developers of AI-enabled software systems need to take into account various novel cyber-attacks and vulnerabilities that these systems may be susceptible to. This paper presents a framework to characterize attacks and weaknesses associated with AI-enabled systems and provide mitigation techniques and defense strategies. This framework aims to support software designers in taking proactive measures in developing AI-enabled software, understanding the attack surface of such systems, and developing products that are resilient to various emerging attacks associated with ML. The developed framework covers a broad spectrum of attacks, mitigation techniques, and defensive and offensive tools. In this paper, we demonstrate the framework architecture and its major components, describe their attributes, and discuss the long-term goals of this research.

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。

↑