Authentic Learning Approach for Artificial Intelligence Systems Security and Privacy

被引：1

作者：

Akter, Shapna ^{[1
]}

Shahriar, Hossain ^{[2
]}

Lo, Dan ^{[1
]}

Sakib, Nazmus ^{[1
]}

Qian, Kai ^{[1
]}

Whitman, Michael ^{[3
]}

Wu, Fan ^{[4
]}

机构：

[1] Kennesaw State Univ, Dept Comp Sci, Kennesaw, GA 30144 USA

[2] Kennesaw State Univ, Dept Informat Technol, Kennesaw, GA USA

[3] Kennesaw State Univ, Dept Informat Syst & Secur, Kennesaw, GA USA

[4] Tuskegee Univ, Dept Comp Sci, Tuskegee, AL USA

来源：

2023 IEEE 47TH ANNUAL COMPUTERS, SOFTWARE, AND APPLICATIONS CONFERENCE, COMPSAC | 2023年

基金：

美国国家科学基金会;

关键词：

Authentic learning; ML/DL algorithm; Adversarial attack; Security; Privacy; Education;

D O I：

10.1109/COMPSAC57700.2023.00151

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

The main objective of authentic learning is to offer students an exciting and stimulating educational setting that provides practical experiences in tackling real-world security issues. Each educational theme is composed of pre-lab, lab, and post-lab activities. Through the application of authentic learning, we create and produce portable lab equipment for AI Security and Privacy on Google CoLab. This enables students to access and practice these hands-on labs conveniently and without the need for time-consuming installations and configurations. As a result, students can concentrate more on learning concepts and gain more experience in hands-on problem-solving abilities.

引用

页码：1010 / 1012

页数：3

共 3 条

[1] Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
Fredrikson, Matt
Jha, Somesh
Ristenpart, Thomas
[J]. CCS'15: PROCEEDINGS OF THE 22ND ACM SIGSAC CONFERENCE ON COMPUTER AND COMMUNICATIONS SECURITY, 2015, : 1322 - 1333
[2] Artificial Intelligence Security Threat, Crime, and Forensics: Taxonomy and Open Issues
Jeong, Doowon
[J]. IEEE ACCESS, 2020, 8 : 184560 - 184574
[3] Xu XJ, 2021, P IEEE S SECUR PRIV, P103, DOI [10.1109/SP40001.2021.00034, 10.1109/ICECE54449.2021.9674456]

← 1 →