用专用协处理器解耦动态信息流跟踪

Hari Kannan, Michael Dalton, C. Kozyrakis
{"title":"用专用协处理器解耦动态信息流跟踪","authors":"Hari Kannan, Michael Dalton, C. Kozyrakis","doi":"10.1109/DSN.2009.5270347","DOIUrl":null,"url":null,"abstract":"Dynamic Information Flow Tracking (DIFT) is a promising security technique. With hardware support, DIFT prevents a wide range of attacks on vulnerable software with minimal performance impact. DIFT architectures, however, require significant changes in the processor pipeline that increase design and verification complexity and may affect clock frequency. These complications deter hardware vendors from supporting DIFT. This paper makes hardware support for DIFT cost-effective by decoupling DIFT functionality onto a simple, separate coprocessor. Decoupling is possible because DIFT operations and regular computation need only synchronize on system calls. The coprocessor is a small hardware engine that performs logical operations and caches 4-bit tags. It introduces no changes to the design or layout of the main processor's logic, pipeline, or caches, and can be combined with various processors. Using a full-system hardware prototype and realistic Linux workloads, we show that the DIFT coprocessor provides the same security guarantees as current DIFT architectures with low runtime overheads.","PeriodicalId":376982,"journal":{"name":"2009 IEEE/IFIP International Conference on Dependable Systems & Networks","volume":"28 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2009-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"82","resultStr":"{\"title\":\"Decoupling Dynamic Information Flow Tracking with a dedicated coprocessor\",\"authors\":\"Hari Kannan, Michael Dalton, C. Kozyrakis\",\"doi\":\"10.1109/DSN.2009.5270347\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Dynamic Information Flow Tracking (DIFT) is a promising security technique. With hardware support, DIFT prevents a wide range of attacks on vulnerable software with minimal performance impact. DIFT architectures, however, require significant changes in the processor pipeline that increase design and verification complexity and may affect clock frequency. These complications deter hardware vendors from supporting DIFT. This paper makes hardware support for DIFT cost-effective by decoupling DIFT functionality onto a simple, separate coprocessor. Decoupling is possible because DIFT operations and regular computation need only synchronize on system calls. The coprocessor is a small hardware engine that performs logical operations and caches 4-bit tags. It introduces no changes to the design or layout of the main processor's logic, pipeline, or caches, and can be combined with various processors. Using a full-system hardware prototype and realistic Linux workloads, we show that the DIFT coprocessor provides the same security guarantees as current DIFT architectures with low runtime overheads.\",\"PeriodicalId\":376982,\"journal\":{\"name\":\"2009 IEEE/IFIP International Conference on Dependable Systems & Networks\",\"volume\":\"28 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2009-09-29\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"82\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2009 IEEE/IFIP International Conference on Dependable Systems & Networks\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/DSN.2009.5270347\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2009 IEEE/IFIP International Conference on Dependable Systems & Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DSN.2009.5270347","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 82

摘要

动态信息流跟踪(DIFT)是一种很有前途的安全技术。有了硬件支持,DIFT可以在对易受攻击的软件造成最小性能影响的情况下防止各种攻击。然而,DIFT架构需要对处理器管道进行重大更改,这会增加设计和验证的复杂性,并可能影响时钟频率。这些复杂性阻碍了硬件供应商支持DIFT。本文通过将DIFT功能解耦到一个简单、独立的协处理器上,使DIFT的硬件支持具有成本效益。解耦是可能的,因为DIFT操作和常规计算只需要在系统调用上同步。协处理器是一个小型硬件引擎,执行逻辑操作并缓存4位标签。它不会改变主处理器的逻辑、管道或缓存的设计或布局,并且可以与各种处理器结合使用。使用完整的系统硬件原型和实际的Linux工作负载,我们展示了DIFT协处理器提供与当前DIFT体系结构相同的安全保证,并且运行时开销较低。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
Decoupling Dynamic Information Flow Tracking with a dedicated coprocessor
Dynamic Information Flow Tracking (DIFT) is a promising security technique. With hardware support, DIFT prevents a wide range of attacks on vulnerable software with minimal performance impact. DIFT architectures, however, require significant changes in the processor pipeline that increase design and verification complexity and may affect clock frequency. These complications deter hardware vendors from supporting DIFT. This paper makes hardware support for DIFT cost-effective by decoupling DIFT functionality onto a simple, separate coprocessor. Decoupling is possible because DIFT operations and regular computation need only synchronize on system calls. The coprocessor is a small hardware engine that performs logical operations and caches 4-bit tags. It introduces no changes to the design or layout of the main processor's logic, pipeline, or caches, and can be combined with various processors. Using a full-system hardware prototype and realistic Linux workloads, we show that the DIFT coprocessor provides the same security guarantees as current DIFT architectures with low runtime overheads.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Evaluating the impact of Undetected Disk Errors in RAID systems Remote attestation to dynamic system properties: Towards providing complete system integrity evidence Processor reliability enhancement through compiler-directed register file peak temperature reduction Intrusion-tolerant self-healing devices for critical infrastructure protection A simple equation for estimating reliability of an N+1 redundant array of independent disks (RAID)
×
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