arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.15764cs.AIcs.CRcs.CYcs.LG
收藏

攻击性AI对组织的威胁

The Threat of Offensive AI to Organizations

Ben-Gurion University(本-古里安大学);University of Cagliari(卡利亚里大学);Microsoft(微软);Nanyang Technological University(南洋理工大学);Purdue(普渡大学);Georgia Institute of Technology(佐治亚理工学院);Pluribus One(Pluribus One公司)

Yisroel Mirsky, Ambra Demontis, Jaidip Kotak, Ram Shankar, Deng Gelei, Liu Yang, Xiangyu Zhang, Wenke Lee, Yuval Elovici, Battista Biggio

摘要:

人工智能为我们提供了自动化任务的能力,从大量数据中提取信息,并合成与真实事物几乎无法区分的媒体。然而,积极的工具也可以用于消极的目的。特别是,网络对手可以使用人工智能(如机器学习)来增强攻击并扩大活动。尽管过去已经讨论过攻击性人工智能,但仍然需要在组织的背景下分析和理解威胁。例如,具有AI能力的对手如何影响网络杀戮链?AI对攻击者的好处比对防御者的好处多吗?组织目前面临的最大的AI威胁是什么,它们对未来的影响是什么?在这项调查中,我们探讨了攻击性人工智能对组织的威胁。首先,我们介绍背景,并讨论人工智能如何改变对手的方法,策略,目标和整体攻击模型。然后,通过文献回顾,我们确定了33种攻击性AI功能,对手可以使用这些功能来增强他们的攻击。最后,通过跨行业和学术界的用户研究,我们对AI威胁进行了排名,并提供了对对手的见解。

英文摘要:

AI has provided us with the ability to automate tasks, extract information from vast amounts of data, and synthesize media that is nearly indistinguishable from the real thing. However, positive tools can also be used for negative purposes. In particular, cyber adversaries can use AI (such as machine learning) to enhance their attacks and expand their campaigns. Although offensive AI has been discussed in the past, there is a need to analyze and understand the threat in the context of organizations. For example, how does an AI-capable adversary impact the cyber kill chain? Does AI benefit the attacker more than the defender? What are the most significant AI threats facing organizations today and what will be their impact on the future? In this survey, we explore the threat of offensive AI on organizations. First, we present the background and discuss how AI changes the adversary's methods, strategies, goals, and overall attack model. Then, through a literature review, we identify 33 offensive AI capabilities which adversaries can use to enhance their attacks. Finally, through a user study spanning industry and academia, we rank the AI threats and provide insights on the adversaries.

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。

↑