arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.18669cs.CRcs.AIcs.CY
收藏

“隐蔽式安全”的陷阱及其对透明AI的意义

The Pitfalls of "Security by Obscurity" And What They Mean for Transparent AI

New York University(纽约大学)

Peter Hall, Olivia Mundahl, Sunoo Park

AI总结:

本文探讨了AI界如何从计算机安全界抵制“隐蔽式安全”的经验中汲取关于透明度的见解,通过三个关键主题和匿名化案例研究,分析了AI透明度的相似性与独特挑战。

摘要:

从监管机构、研究人员到用户等各方利益相关者,要求AI系统透明化的呼声在数量和紧迫性上日益增长(相比之下,开发AI的公司则较少提出此类要求)。关于AI透明度的概念比比皆是,每个概念都针对不同的利益和关切。在计算机安全领域,透明度同样被视为一个关键概念。几十年来,面对来自行业和其他利益相关者的巨大压力,安全界一直抵制所谓的“隐蔽式安全”——即认为隐藏系统的工作原理就能使其免受攻击的观念。在过去几十年中,在一个不完美且仍在进行的社区过程中,安全研究人员和从业者逐渐建立了一些规范和实践,以平衡透明度利益与可能的负面副作用。本文提出:AI界可以从安全界在透明度方面的经验中汲取哪些见解?我们确定了安全界关于透明度益处的观点及其平衡透明度与对抗性利益的方法的三个关键主题。针对每个主题,我们调查了与AI透明度相关的相似之处和见解。然后,我们提供了一个关于透明度如何塑造匿名化研究子领域的案例研究讨论。最后,将焦点从相似性转向差异性,我们强调了现代AI系统呈现出不同于其他类型安全关键系统挑战的关键透明度问题,为安全界和AI界提出了有趣的开放性问题。

英文摘要:

Calls for transparency in AI systems are growing in number and urgency from diverse stakeholders ranging from regulators to researchers to users (with a comparative absence of companies developing AI). Notions of transparency for AI abound, each addressing distinct interests and concerns. In computer security, transparency is likewise regarded as a key concept. The security community has for decades pushed back against so-called security by obscurity -- the idea that hiding how a system works protects it from attack -- against significant pressure from industry and other stakeholders. Over the decades, in a community process that is imperfect and ongoing, security researchers and practitioners have gradually built up some norms and practices around how to balance transparency interests with possible negative side effects. This paper asks: What insights can the AI community take from the security community's experience with transparency? We identify three key themes in the security community's perspective on the benefits of transparency and their approach to balancing transparency against countervailing interests. For each, we investigate parallels and insights relevant to transparency in AI. We then provide a case study discussion on how transparency has shaped the research subfield of anonymization. Finally, shifting our focus from similarities to differences, we highlight key transparency issues where modern AI systems present challenges different from other kinds of security-critical systems, raising interesting open questions for the security and AI communities alike.

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。

↑