Supporting Artificial Intelligence/Machine Learning Security Workers Through an Adversarial Techniques, Tools, and Common Knowledge Framework

被引:6
作者
Fazelnia, Mohamad [1 ]
Okutan, Ahmet [1 ]
Mirakhorli, Mehdi [1 ,2 ]
机构
[1] Rochester Inst Technol, Global Cybersecur Inst, Rochester, NY 14623 USA
[2] Rochester Inst Technol, Dept Software Engn, Rochester, NY 14623 USA
关键词
Security; Artificial intelligence; Computer security; Data models; Task analysis; Training; Robustness;
D O I
10.1109/MSEC.2022.3221058
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This article focuses on supporting artificial intelligence (AI)/machine learning (ML) security workers. It presents AI/ML adversarial techniques, tools, and common knowledge (AI/ML ATT & CK) framework to enable AI/ML security workers to intuitively explore offensive and defensive tactics.
引用
收藏
页码:37 / 48
页数:12
相关论文
共 14 条
[1]   Software Engineering for Machine Learning: A Case Study [J].
Amershi, Saleema ;
Begel, Andrew ;
Bird, Christian ;
DeLine, Robert ;
Gall, Harald ;
Kamar, Ece ;
Nagappan, Nachiappan ;
Nushi, Besmira ;
Zimmermann, Thomas .
2019 IEEE/ACM 41ST INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING: SOFTWARE ENGINEERING IN PRACTICE (ICSE-SEIP 2019), 2019, :291-300
[2]  
[Anonymous], Common Weakness Enumeration
[3]  
ATT&CK Threat Database, About us
[4]  
Bughin J., 2018, MCKINSEY GLOBAL I, V1, P3
[5]  
Fazelnia M., 2021, PROC 9 INT C LEARNIN
[6]  
Haney JM, 2021, INF COMPUT SECUR, V29, P485, DOI [10.1108/ICS-08-2020-0131, 10.1108/ics-08-2020-0131]
[7]  
Huang L., 2011, ACM WORKSHOP SECURIT, P43, DOI [DOI 10.1145/2046684.2046692, 10.1145/2046684.2046692]
[8]  
Jia SS, 2018, 2018 IEEE SYMPOSIUM ON PRODUCT COMPLIANCE ENGINEERING - ASIA 2018 (IEEE ISPCE-CN 2018), P94
[9]  
Kitchenham B., 2004, PROCEDURES PERFORMIN, V33, P28, DOI DOI 10.5144/0256-4947.2017.79
[10]   The Limitations of Deep Learning in Adversarial Settings [J].
Papernot, Nicolas ;
McDaniel, Patrick ;
Jha, Somesh ;
Fredrikson, Matt ;
Celik, Z. Berkay ;
Swami, Ananthram .
1ST IEEE EUROPEAN SYMPOSIUM ON SECURITY AND PRIVACY, 2016, :372-387