arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.13250cs.LGcs.CRcs.CYcs.SE
收藏

推进有保证的人工智能和机器学习能力的研究和开发

Advancing the Research and Development of Assured Artificial Intelligence and Machine Learning Capabilities

U.S. Army Combat Capabilities Development Command C5ISR Center(美国陆军战斗能力发展司令部C5ISR中心);U.S. Army Combat Capabilities Development Command Army Research Laboratory(美国陆军战斗能力发展司令部陆军研究实验室);U.S. Military Academy Army Cyber Institute(美国陆军军官学院陆军网络研究所);U.S. Department of Defense Joint Artificial Intelligence Center(美国国防部联合人工智能中心)

Tyler J. Shipp, Daniel J. Clouse, Michael J. De Lucia, Metin B. Ahiskali, Kai Steverson, Jonathan M. Mullin, Nathaniel D. Bastian

摘要:

人工智能(AI)和机器学习(ML)在所有战争领域的新型防御和情报能力的发展中变得越来越重要。对抗性AI(A2 I)和对抗性ML(AML)攻击试图欺骗和操纵AI/ML模型。AI/ML模型必须能够抵御这些攻击。A2 I/AML防御将有助于为这些使用AI/ML模型的高级功能提供必要的保证。A2 I工作组(A2 IWG)旨在通过在美国国防部和美国情报界建立协作环境,通过新的A2 I/AML防御来推进有保证的AI/ML能力的研究和开发。A2 IWG旨在确定它可以帮助解决或更直接解决的具体挑战,最初关注三个主题:AI可信鲁棒性,AI系统安全性和AI/ML架构漏洞。

英文摘要:

Artificial intelligence (AI) and machine learning (ML) have become increasingly vital in the development of novel defense and intelligence capabilities across all domains of warfare. An adversarial AI (A2I) and adversarial ML (AML) attack seeks to deceive and manipulate AI/ML models. It is imperative that AI/ML models can defend against these attacks. A2I/AML defenses will help provide the necessary assurance of these advanced capabilities that use AI/ML models. The A2I Working Group (A2IWG) seeks to advance the research and development of assured AI/ML capabilities via new A2I/AML defenses by fostering a collaborative environment across the U.S. Department of Defense and U.S. Intelligence Community. The A2IWG aims to identify specific challenges that it can help solve or address more directly, with initial focus on three topics: AI Trusted Robustness, AI System Security, and AI/ML Architecture Vulnerabilities.

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。

↑