Spotlight: An Impairing Packet Transmission Attack Targeting Specific Node in NoC-based TCMP

Jiaoyan Yao, Ying Zhang, Yifeng Hua, Yuanxiang Li, Jizhong Yang, Xin Chen
{"title":"Spotlight: An Impairing Packet Transmission Attack Targeting Specific Node in NoC-based TCMP","authors":"Jiaoyan Yao, Ying Zhang, Yifeng Hua, Yuanxiang Li, Jizhong Yang, Xin Chen","doi":"10.1109/ETS56758.2023.10174197","DOIUrl":null,"url":null,"abstract":"As the communication infrastructure utilized by Tiled Chip Multicore Processors (TCMP), Network-on-Chip (NoC) has been subject to serious security vulnerabilities due to hardware Trojans (HTs) concealed in potentially insecure 3PIPs. To satisfy the need for secure NoCs, it is vital to model potential attacks and analyze their impacts on NoC performance. This paper proposes a novel and covert HT model called Spotlight targeting specific victim node in XY-routing NoC to optimize the attacking effect. By inserting Trojans into special nodes and modifying the arbiters of input ports within the switch allocator of router, packets flowing to the victim node are unfairly treated causing considerable latency. As a result, the HT effectively degrades the transmission of packets while having a subtle impact on other NoC performance. The proposed HT is inserted into Garnet 2.0 of Gem5 simulator for performance evaluation. Experimental results indicate that the Spotlight attack increased the average delay of target packets by 12.16 cycles. Compared to some DoS attacks, the proposed Trojan affected packet transmission with fewer packets, causing minimal fluctuates in NoC metrics such as average latency. And the area and power overheads are only 0.94% and 0.11%, respectively.","PeriodicalId":211522,"journal":{"name":"2023 IEEE European Test Symposium (ETS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 IEEE European Test Symposium (ETS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ETS56758.2023.10174197","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

As the communication infrastructure utilized by Tiled Chip Multicore Processors (TCMP), Network-on-Chip (NoC) has been subject to serious security vulnerabilities due to hardware Trojans (HTs) concealed in potentially insecure 3PIPs. To satisfy the need for secure NoCs, it is vital to model potential attacks and analyze their impacts on NoC performance. This paper proposes a novel and covert HT model called Spotlight targeting specific victim node in XY-routing NoC to optimize the attacking effect. By inserting Trojans into special nodes and modifying the arbiters of input ports within the switch allocator of router, packets flowing to the victim node are unfairly treated causing considerable latency. As a result, the HT effectively degrades the transmission of packets while having a subtle impact on other NoC performance. The proposed HT is inserted into Garnet 2.0 of Gem5 simulator for performance evaluation. Experimental results indicate that the Spotlight attack increased the average delay of target packets by 12.16 cycles. Compared to some DoS attacks, the proposed Trojan affected packet transmission with fewer packets, causing minimal fluctuates in NoC metrics such as average latency. And the area and power overheads are only 0.94% and 0.11%, respectively.
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
聚焦:基于noc的tcp协议中针对特定节点的破坏性数据包传输攻击
作为平铺式芯片多核处理器(TCMP)使用的通信基础设施,片上网络(NoC)由于隐藏在潜在不安全的3pip中的硬件木马(ht)而受到严重的安全漏洞的影响。为了满足对安全NoC的需求,对潜在攻击进行建模并分析其对NoC性能的影响至关重要。针对xy路由NoC中特定受害节点,提出了一种新颖的隐蔽HT模型Spotlight,以优化攻击效果。通过在特殊节点中插入木马并修改路由器的交换机分配器中的输入端口仲裁器,流向受害节点的数据包会受到不公平的处理,导致相当大的延迟。因此,高温有效地降低了数据包的传输,同时对其他NoC性能产生了微妙的影响。将所提出的HT插入Gem5模拟器的Garnet 2.0中进行性能评估。实验结果表明,Spotlight攻击使目标数据包的平均延迟增加了12.16个周期。与某些DoS攻击相比,该木马影响的数据包传输数量更少,导致平均延迟等NoC指标波动最小。面积开销和功耗开销分别仅为0.94%和0.11%。
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
自引率
0.00%
发文量
0
期刊最新文献
Counterfeit Detection by Semiconductor Process Technology Inspection Semi-Supervised Deep Learning for Microcontroller Performance Screening FINaL: Driving High-Level Fault Injection Campaigns with Natural Language Learn to Tune: Robust Performance Tuning in Post-Silicon Validation A Resilience Framework for Synapse Weight Errors and Firing Threshold Perturbations in RRAM Spiking Neural Networks
×
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