Security Enhancement Through Compiler-Assisted Software Diversity With Deep Reinforcement Learning

IF 0.6 Q4 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS International Journal of Digital Crime and Forensics Pub Date : 2022-07-01 DOI:10.4018/ijdcf.302878
Junchao Wang, Jin Wei, J. Pang, Fan Zhang, Shunbin Li
{"title":"Security Enhancement Through Compiler-Assisted Software Diversity With Deep Reinforcement Learning","authors":"Junchao Wang, Jin Wei, J. Pang, Fan Zhang, Shunbin Li","doi":"10.4018/ijdcf.302878","DOIUrl":null,"url":null,"abstract":"Traditional software defenses take corresponding actions after the attacks are discovered. The defenders in this situation are comparatively passive because the attackers may try many different ways to find vulnerability and bugs but the software remains static. This leads to the imbalance between offense and defense. Software diversity alleviates the current threats by implementing a heterogeneous software system. The N-Variant eXecution (NVX) systems, effective and applicable runtime diversifying methods, apply multiple variants to imporove software security. Higher diversity can lead to less vulnerabilities that attacks can exploit. However, runtime diversifying methods such as address randomization and reverse stack can only provide limited diversity to the system. Thus, we enhance the diversity of variants with a compiler-assisted approach. We use a Deep Reinforcement Learning-based algorithm to generate variants, ensuring the high diversity of the system. For different numbers of variants, we show the results of the Deep Q Network algorithm under different parameter settings.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":null,"pages":null},"PeriodicalIF":0.6000,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Digital Crime and Forensics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.4018/ijdcf.302878","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0

Abstract

Traditional software defenses take corresponding actions after the attacks are discovered. The defenders in this situation are comparatively passive because the attackers may try many different ways to find vulnerability and bugs but the software remains static. This leads to the imbalance between offense and defense. Software diversity alleviates the current threats by implementing a heterogeneous software system. The N-Variant eXecution (NVX) systems, effective and applicable runtime diversifying methods, apply multiple variants to imporove software security. Higher diversity can lead to less vulnerabilities that attacks can exploit. However, runtime diversifying methods such as address randomization and reverse stack can only provide limited diversity to the system. Thus, we enhance the diversity of variants with a compiler-assisted approach. We use a Deep Reinforcement Learning-based algorithm to generate variants, ensuring the high diversity of the system. For different numbers of variants, we show the results of the Deep Q Network algorithm under different parameter settings.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
通过深度强化学习的编译器辅助软件多样性来增强安全性
传统的软件防御是在发现攻击后才采取相应的防御措施。在这种情况下,防御者相对被动,因为攻击者可能尝试许多不同的方法来寻找漏洞和错误,但软件保持静态。这导致了进攻和防守的不平衡。软件多样性通过实现异构软件系统减轻了当前的威胁。NVX (N-Variant eXecution)系统是一种有效且适用的运行时多样化方法,可以应用多种变体来提高软件的安全性。更高的多样性可以减少攻击可利用的漏洞。然而,运行时多样化的方法,如地址随机化和反向堆栈只能为系统提供有限的多样性。因此,我们用编译器辅助的方法增强了变体的多样性。我们使用基于深度强化学习的算法来生成变量,确保系统的高度多样性。对于不同数量的变量,我们展示了Deep Q Network算法在不同参数设置下的结果。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
International Journal of Digital Crime and Forensics
International Journal of Digital Crime and Forensics COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS-
CiteScore
2.70
自引率
0.00%
发文量
15
期刊最新文献
Efficient Task Offloading for Mobile Edge Computing in Vehicular Networks Examining the Behavior of Web Browsers Using Popular Forensic Tools Laboratory Dangerous Operation Behavior Detection System Based on Deep Learning Algorithm A Novel Watermarking Scheme for Audio Data Stored in Third Party Servers Assurance of Network Communication Information Security Based on Cyber-Physical Fusion and Deep Learning
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1