arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2412.09751cs.CYcs.AIcs.HC
收藏

AI红队测试是社会技术问题:关于价值观、劳动与危害

AI red-teaming is a sociotechnical problem: on values, labor, and harms

Microsoft Research(微软研究院);University of Southern California(南加州大学)

Tarleton Gillespie, Ryland Shaw, Mary L. Gray, Jina Suh

AI总结:

本文探讨AI红队测试作为社会技术问题的重要性,强调需跨学科合作以理解其价值观、劳动及影响,避免重复历史错误。

摘要:

随着生成式AI技术在现实世界中的应用日益增多,测试其性能和安全性的重要性显得尤为关键。'红队测试'已迅速成为测试AI模型的主要方法——被AI公司优先考虑,并被纳入AI政策和监管中。红队成员扮演对抗者的角色,探测AI系统以测试其安全机制并发现漏洞。然而,我们对这项工作的了解实在太少了,也对其影响知之甚少。本文呼吁计算机科学家和社会科学家合作,研究围绕AI技术的社会技术系统,包括红队测试的工作,以避免重蹈近期的覆辙。我们强调了理解红队测试背后的价值观和假设、所涉及的劳动安排以及对红队成员的心理影响的重要性,借鉴内容审核工作的经验教训。

英文摘要:

As generative AI technologies find more and more real-world applications, the importance of testing their performance and safety seems paramount. "Red-teaming" has quickly become the primary approach to test AI models--prioritized by AI companies, and enshrined in AI policy and regulation. Members of red teams act as adversaries, probing AI systems to test their safety mechanisms and uncover vulnerabilities. Yet we know far too little about this work or its implications. This essay calls for collaboration between computer scientists and social scientists to study the sociotechnical systems surrounding AI technologies, including the work of red-teaming, to avoid repeating the mistakes of the recent past. We highlight the importance of understanding the values and assumptions behind red-teaming, the labor arrangements involved, and the psychological impacts on red-teamers, drawing insights from the lessons learned around the work of content moderation.

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。

↑