Open problems in the security of learning
Open problems in the security of learning
复制标题
学习安全中的开放性问题
DOI：
--
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
J. D. Tygar
中科院分区：
文献类型：
--
作者：
M. Barreno;P. Bartlett;F. J. Chi;A. Joseph;B. Nelson;Benjamin I. P. Rubinstein;Udam Saini;J. D. Tygar
机器学习已经成为检测和预防恶意活动的重要工具。然而，随着越来越多的应用程序在对抗性决策情境中使用机器学习技术，针对机器学习系统的越来越强大的攻击成为可能。在本文中，我们提出了开发真正安全学习的三个主要研究方向。首先，我们建议找到对抗性影响的界限对于理解攻击者对学习系统能做什么和不能做什么是很重要的。其次，我们调查了对抗能力的价值——攻击的成功在很大程度上取决于攻击者拥有什么类型的信息和影响。最后，我们提出了安全学习技术的发展方向，并提出了对抗性环境中安全学习技术的研究方向。我们打算在本文中促进关于机器学习安全性的讨论，我们相信我们提出的研究方向代表了在追求安全学习的过程中最重要的方向。
Machine learning has become a valuable tool for detecting and preventing malicious activity. However, as more applications employ machine learning techniques in adversarial decision-making situations, increasingly powerful attacks become possible against machine learning systems. In this paper, we present three broad research directions towards the end of developing truly secure learning. First, we suggest that finding bounds on adversarial influence is important to understand the limits of what an attacker can and cannot do to a learning system. Second, we investigate the value of adversarial capabilities-the success of an attack depends largely on what types of information and influence the attacker has. Finally, we propose directions in technologies for secure learning and suggest lines of investigation into secure techniques for learning in adversarial environments. We intend this paper to foster discussion about the security of machine learning, and we believe that the research directions we propose represent the most important directions to pursue in the quest for secure learning.