arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.07205cs.CRcs.LGstat.ML
收藏

现实世界中的安全和机器学习

Security and Machine Learning in the Real World

University of Washington(华盛顿大学);Microsoft Research(微软研究院)

Ivan Evtimov, Weidong Cui, Ece Kamar, Emre Kiciman, Tadayoshi Kohno, Jerry Li

摘要:

部署在许多安全和业务关键型系统中的机器学习(ML)模型很容易通过对抗性示例被利用。大量的学术研究已经彻底探索了这些盲点的原因,开发了寻找它们的复杂算法,并提出了一些有前途的防御措施。然而,这些作品中的绝大多数研究独立的神经网络模型。在这项工作中,我们建立在我们的经验,评估大规模部署的机器学习软件产品的安全性,以扩大对话,包括这些漏洞的系统安全视图。我们描述了在具有ML组件的软件中实现系统安全最佳实践的新挑战。此外,我们还提出了一系列短期缓解建议,部署机器学习模块的从业者可以使用这些建议来保护他们的系统。最后,我们概述了机器学习攻击和防御的新研究方向,这些攻击和防御可以促进ML系统的安全性。

英文摘要:

Machine learning (ML) models deployed in many safety- and business-critical systems are vulnerable to exploitation through adversarial examples. A large body of academic research has thoroughly explored the causes of these blind spots, developed sophisticated algorithms for finding them, and proposed a few promising defenses. A vast majority of these works, however, study standalone neural network models. In this work, we build on our experience evaluating the security of a machine learning software product deployed on a large scale to broaden the conversation to include a systems security view of these vulnerabilities. We describe novel challenges to implementing systems security best practices in software with ML components. In addition, we propose a list of short-term mitigation suggestions that practitioners deploying machine learning modules can use to secure their systems. Finally, we outline directions for new research into machine learning attacks and defenses that can serve to advance the state of ML systems security.

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。

↑