Festus Hategekimana, Pierre-Alexis Nardin, C. Bobda
{"title":"Hardware/Software Isolation and Protection Architecture for Transparent Security Enforcement in Networked Devices","authors":"Festus Hategekimana, Pierre-Alexis Nardin, C. Bobda","doi":"10.1109/ISVLSI.2016.32","DOIUrl":null,"url":null,"abstract":"We present an integrated hardware/software architectureto enforce security in networked workstations andembedded devices such as printers and microscopes. Thesedevices are usually connected to the Internet without protection, so they are exposed to attack. Our solution operatesas an intermediate isolation and protection module (IPM) between the network and the device to be protected. TheIPM can be implemented as a dedicated IP on a system-onchip, or as a separate chip to analyze incoming and outgoingtraffic for malicious activities, in a transparent way to thedevice under protection. Security enforcement is performedin two stages. A deep packet inspection module is used inthe first stage to detect and drop packets originating fromknown blacklisted domains or carrying malware patterns, simultaneously important features from protocol-conformingpackets are extracted and sent to a binary classifier for furtherprocessing and decision making. The second stage uses a binaryclassifier to make decisions on seemingly protocol-conformingpackets. We designed and implemented a prototype of theIPM as a system-on-FPGA, with packet filtering and analysisaccelerated in hardware, and binary classification and decisionmaking in software. The IPM operates at high-speed witha very small footprint, suitable for embedded devices withfewer resources. Evaluation of our prototype using the 1999Knowledge Discovery in Databases (KDD Cup 1999 dataset) benchmarks shows a high detection rate on various distributeddenial-of-service (DDoS) attacks such as Neptune DoS (99.3%),Smurf DoS (100%), and Teardrop DoS (98.90%).","PeriodicalId":140647,"journal":{"name":"2016 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2016-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 IEEE Computer Society Annual Symposium on VLSI (ISVLSI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ISVLSI.2016.32","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
Abstract
We present an integrated hardware/software architectureto enforce security in networked workstations andembedded devices such as printers and microscopes. Thesedevices are usually connected to the Internet without protection, so they are exposed to attack. Our solution operatesas an intermediate isolation and protection module (IPM) between the network and the device to be protected. TheIPM can be implemented as a dedicated IP on a system-onchip, or as a separate chip to analyze incoming and outgoingtraffic for malicious activities, in a transparent way to thedevice under protection. Security enforcement is performedin two stages. A deep packet inspection module is used inthe first stage to detect and drop packets originating fromknown blacklisted domains or carrying malware patterns, simultaneously important features from protocol-conformingpackets are extracted and sent to a binary classifier for furtherprocessing and decision making. The second stage uses a binaryclassifier to make decisions on seemingly protocol-conformingpackets. We designed and implemented a prototype of theIPM as a system-on-FPGA, with packet filtering and analysisaccelerated in hardware, and binary classification and decisionmaking in software. The IPM operates at high-speed witha very small footprint, suitable for embedded devices withfewer resources. Evaluation of our prototype using the 1999Knowledge Discovery in Databases (KDD Cup 1999 dataset) benchmarks shows a high detection rate on various distributeddenial-of-service (DDoS) attacks such as Neptune DoS (99.3%),Smurf DoS (100%), and Teardrop DoS (98.90%).
我们提出了一个集成的硬件/软件架构,以加强网络工作站和嵌入式设备(如打印机和显微镜)的安全性。这些设备通常在没有保护的情况下连接到互联网,因此它们很容易受到攻击。我们的解决方案作为网络和受保护设备之间的中间隔离和保护模块(IPM)运行。ipm可以作为片上系统的专用IP来实现,也可以作为一个单独的芯片来分析恶意活动的传入和传出流量,以一种对受保护设备透明的方式。安全实施分两个阶段执行。在第一阶段使用深度包检测模块来检测和丢弃来自已知黑名单域或携带恶意软件模式的数据包,同时从符合协议的数据包中提取重要特征并发送给二分类器进行进一步处理和决策。第二阶段使用二进制分类器对看似符合协议的数据包做出决策。我们设计并实现了ipm的原型,作为fpga上的系统,在硬件上加速包过滤和分析,在软件上加速二进制分类和决策。IPM以高速运行,占用空间非常小,适合资源较少的嵌入式设备。使用1999年数据库知识发现(KDD Cup 1999数据集)基准测试对我们的原型进行评估,显示出对各种分布式拒绝服务(DDoS)攻击的高检测率,例如Neptune DoS (99.3%),Smurf DoS(100%)和Teardrop DoS(98.90%)。