DevTag: A Benchmark for Fingerprinting IoT Devices

计算机科学 水准点(测量) 指纹(计算) 物联网 网络数据包 数据挖掘 实时计算 计算机网络 嵌入式系统 人工智能 大地测量学 地理
作者
Shangfeng Wan,Qiang Li,Haining Wang,Hong Li,Limi Sun
出处
期刊:IEEE Internet of Things Journal [Institute of Electrical and Electronics Engineers]
卷期号:10 (7): 6388-6399 被引量:20
标识
DOI:10.1109/jiot.2022.3225580
摘要

Nowadays, various Internet of Things (IoT) devices, such as routers, webcams, and network printers, have been deployed across the Internet. For security and management purposes, it is important to accurately fingerprint IoT devices. In this work, we build a first benchmark called DevTag (IoT Device Tagging) for fingerprinting IoT devices. Specifically, DevTag supports retrieving packet-level features from IoT devices through two different data collections, passive monitoring, and active probing. For detecting IoT devices, DevTag integrates model-based and rule-based fingerprinting methods. For the model-based detection, we reimplemented five typical deep algorithms to infer IoT device classification models. For the rule-based detection, we generated nearly 41 117 rules in a unified format by analyzing several open-source tools. Furthermore, we conducted a systematic analysis to explore the advantages and limitations of those two methods for detecting IoT devices. Our analysis results reveal that the model-based detection has a significant advantage in distinguishing coarse-grained IoT devices (e.g., device type and vendor), while it is not suitable to detect product information as the label amount is massive. The rule-based detection is capable of extracting fine-grained device information with high precision in a short time. However, rules also suffer several inherent problems, such as multiple matching, conflicting, and overlapping issues. Finally, we implemented and distributed a prototype of DevTag working as the first benchmark for detecting IoT devices in the network community.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
猫与咖啡完成签到,获得积分10
刚刚
刚刚
阿申爱乐的应助被来一杯忌廉采纳,获得30
刚刚
Hello的应助被球球了采纳,获得10
刚刚
phc发布了新的文献求助10
1秒前
强健的八宝粥完成签到,获得积分10
1秒前
llll发布了新的文献求助10
1秒前
RRRenaissance完成签到,获得积分20
1秒前
1秒前
1秒前
annie完成签到,获得积分10
2秒前
2秒前
上官若男的应助被songyewen采纳,获得10
2秒前
Yu完成签到,获得积分10
2秒前
平淡灵槐发布了新的文献求助10
2秒前
2秒前
爱的痛了发布了新的文献求助10
3秒前
风趣秋灵完成签到,获得积分10
3秒前
张涵颖完成签到,获得积分20
3秒前
3秒前
张子文发布了新的文献求助10
3秒前
4秒前
月亮不会去茶山约会完成签到,获得积分10
4秒前
5秒前
郑方舟完成签到,获得积分20
6秒前
6秒前
卡巴涛的应助被123456789采纳,获得10
6秒前
慕青的应助被phc采纳,获得10
6秒前
张涵颖发布了新的文献求助10
6秒前
6秒前
6秒前
Berry完成签到,获得积分10
7秒前
7秒前
7秒前
李健的应助被炘儿采纳,获得10
8秒前
8秒前
戒骄戒躁发布了新的文献求助10
8秒前
XxmG发布了新的文献求助10
8秒前
8秒前
8秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
Resource Recovery Handbook 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8176174
求助须知:如何正确求助?哪些是违规求助? 9567656
关于积分的说明 21793895
捐赠科研通 7770887
什么是DOI,文献DOI怎么找? 3431991
关于科研通互助平台的介绍 2556313
邀请新用户注册赠送积分活动 2477540