Mitigating Insecure Outputs in Large Language Models(LLMs): A Practical Educational Module-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Mitigating Insecure Outputs in Large Language Models(LLMs): A Practical Educational Module

Published:2024-07-02 Issue: Volume:1 Page:2424-2429
ISSN:
Container-title:2024 IEEE 48th Annual Computers, Software, and Applications Conference (COMPSAC)
language:
Short-container-title:

Author:

Barek MD Abdul¹,Rahman Md Mostafizur²,Akter Shapna¹,Islam Riad A.B.M Kamrul¹,Rahman Md Abdur¹,Shahriar Hossain³,Rahman Akond⁴,Wu Fan⁵

Affiliation:

1. University of West Florida,Department of Intelligent Systems and Robotics,USA

2. University of West Florida,Dept. of Cybersecurity and Information Technology,USA

3. Center for Cybersecurity, University of West Florida,USA

4. Auburn University,Computer Science and Software Engineering,USA

5. Tuskegee University,Dept. of Computer Science,USA

Funder

National Science Foundation

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx8/10633276/10633246/10633444.pdf?arnumber=10633444

Reference21 articles.

1. LIm censorship: A machine learning challenge or a computer security problem?;Glukhov;arXiv preprint,2023

2. Authentic learning for the 21st century: An overview;Lombardi;Educause learning initiative,2007

3. Teaching devops security education with hands-on labware: Automated detection of security weakness in python;Akter,2023

4. Security Risk and Attacks in AI: A Survey of Security and Privacy

5. A comparative study on HIPAA technical safeguards assessment of android mHealth applications

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370

www.globalauthorid.com

TOP