SHIL: Self-Supervised Hybrid Learning for Security Attack Detection in Containerized Applications
2022
会议录名称PROCEEDINGS - 2022 IEEE INTERNATIONAL CONFERENCE ON AUTONOMIC COMPUTING AND SELF-ORGANIZING SYSTEMS, ACSOS 2022
页码41-50
发表状态已发表
DOI10.1109/ACSOS55765.2022.00022
摘要

Container security has received much research attention recently. Previous work has proposed to apply various machine learning techniques to detect security attacks in containerized applications. On one hand, supervised machine learning schemes require sufficient labelled training data to achieve good attack detection accuracy. On the other hand, unsupervised machine learning methods are more practical by avoiding training data labelling requirements, but they often suffer from high false alarm rates. In this paper, we present SHIL, a self-supervised hybrid learning solution, which combines unsupervised and supervised learning methods to achieve high accuracy without requiring any manual data labelling. We have implemented a prototype of SHIL and conducted experiments over 41 real world security attacks in 28 commonly used server applications. Our experimental results show that SHIL can reduce false alarms by 39-91% compared to existing supervised or unsupervised machine learning schemes while achieving a higher or similar detection rate. © 2022 IEEE.

会议录编者/会议主办者Google ; IEEE Computer Society ; Protocol Labs ; Smart Contract Research Forum (SCRF)
关键词Errors Learning systems Supervised learning Attack detection Container security Data labelling Hybrid learning Hybrid machine learning Learning schemes Security attack detection Security attacks Supervised machine learning Unsupervised machine learning
会议名称3rd IEEE International Conference on Autonomic Computing and Self-Organizing Systems, ACSOS 2022
出版地10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA
会议地点Virtual, Online, United states
会议日期September 19, 2022 - September 23, 2022
URL查看原文
收录类别EI ; CPCI-S
语种英语
资助项目NSA Science of Security Lablet: Impact through Research, Scientific Methods, and Community Development[H98230-17-D-0080]
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Information Systems ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
WOS记录号WOS:000890265300005
出版者Institute of Electrical and Electronics Engineers Inc.
EI入藏号20224713157654
EI主题词Containers
原始文献类型Conference article (CA)
来源库IEEE
引用统计
正在获取...
文献类型会议论文
条目标识符https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/251431
专题信息科学与技术学院_PI研究组_何静竹组
通讯作者Lin, Yuhang
作者单位
1.North Carolina State Univ, Raleigh, NC 27695 USA
2.ShanghaiTech Univ, Shanghai, Peoples R China
3.Cisco, San Jose, CA USA
推荐引用方式
GB/T 7714
Lin, Yuhang,Tunde-Onadele, Olufogorehan,Gu, Xiaohui,et al. SHIL: Self-Supervised Hybrid Learning for Security Attack Detection in Containerized Applications[C]//Google, IEEE Computer Society, Protocol Labs, Smart Contract Research Forum (SCRF). 10662 LOS VAQUEROS CIRCLE, PO BOX 3014, LOS ALAMITOS, CA 90720-1264 USA:Institute of Electrical and Electronics Engineers Inc.,2022:41-50.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
个性服务
查看访问统计
谷歌学术
谷歌学术中相似的文章
[Lin, Yuhang]的文章
[Tunde-Onadele, Olufogorehan]的文章
[Gu, Xiaohui]的文章
百度学术
百度学术中相似的文章
[Lin, Yuhang]的文章
[Tunde-Onadele, Olufogorehan]的文章
[Gu, Xiaohui]的文章
必应学术
必应学术中相似的文章
[Lin, Yuhang]的文章
[Tunde-Onadele, Olufogorehan]的文章
[Gu, Xiaohui]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。