arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1610.00768cs.LGcs.CRstat.ML
收藏

关于CleverHans v2 .1.0对抗示例库的技术报告

Technical Report on the CleverHans v2.1.0 Adversarial Examples Library

Pennsylvania State University(宾夕法尼亚州立大学);Google Brain(谷歌大脑);University of Toronto(多伦多大学);UC Berkeley(加州大学伯克利分校);Symantec(赛门铁克);Johns Hopkins(约翰斯·霍普金斯大学);The Cooper Union(库珀联盟学院);Nanyang Technological University(南洋理工大学);Kansas State(堪萨斯州立大学);YerevaNN;NTUEE(台湾大学电机工程学系);IIT Delhi(印度理工学院德里分校);MIT(麻省理工学院);Hasso Plattner Institute(哈索·普拉特纳研究所);National Tsing Hua University(国立清华大学);IMPRS(国际马克斯·普朗克研究学院)
Nicolas Papernot, Fartash Faghri, Nicholas Carlini, Ian Goodfellow, Reuben Feinman, Alexey Kurakin, Cihang Xie, Yash Sharma, Tom Brown, Aurko Roy, Alexander Mat… 展开作者

Nicolas Papernot, Fartash Faghri, Nicholas Carlini, Ian Goodfellow, Reuben Feinman, Alexey Kurakin, Cihang Xie, Yash Sharma, Tom Brown, Aurko Roy, Alexander Matyasko, Vahid Behzadan, Karen Hambardzumyan, Zhishuai Zhang, Yi-Lin Juang, Zhi Li, Ryan Sheatsley, Abhibhav Garg, Jonathan Uesato, Willi Gierke, Yinpeng Dong, David Berthelot, Paul Hendricks, Jonas Rauber, Rujun Long, Patrick McDaniel

摘要:

CleverHans是一个软件库,提供对抗性示例构造技术和对抗性训练的标准化参考实现。该库可用于开发更强大的机器学习模型,并提供对抗环境中模型性能的标准化基准。在没有对抗性示例构建的标准化实现的情况下构建的基准彼此不具有可比性,因为良好的结果可能指示鲁棒的模型,或者它可能仅仅指示对抗性示例构建过程的弱实现。本技术报告的结构如下。第1节概述了机器学习和CleverHans软件中的对抗性示例。第2节介绍了库的核心功能:即基于对抗性示例的攻击和防御,以提高机器学习模型对这些攻击的鲁棒性。第3节描述了如何使用库报告基准测试结果。第4节描述了版本控制系统。

英文摘要:

CleverHans is a software library that provides standardized reference implementations of adversarial example construction techniques and adversarial training. The library may be used to develop more robust machine learning models and to provide standardized benchmarks of models' performance in the adversarial setting. Benchmarks constructed without a standardized implementation of adversarial example construction are not comparable to each other, because a good result may indicate a robust model or it may merely indicate a weak implementation of the adversarial example construction procedure. This technical report is structured as follows. Section 1 provides an overview of adversarial examples in machine learning and of the CleverHans software. Section 2 presents the core functionalities of the library: namely the attacks based on adversarial examples and defenses to improve the robustness of machine learning models to these attacks. Section 3 describes how to report benchmark results using the library. Section 4 describes the versioning system.

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。

↑