Deep Learning Based IoT Re-authentication for Botnet Detection and Prevention

Mikail Mohammed Salim; Jong Hyuk Park

doi:10.1007/978-981-32-9244-4_33

Deep Learning Based IoT Re-authentication for Botnet Detection and Prevention

Mikail Mohammed Salim
, Jong Hyuk Park

Dept. of Computer Science and Engineering

Seoul National University of Science and Technology (SNUST)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

IoT devices face a grave security threat from botnet attacks. These devices are known for their poor default authentication system due to being set on weak factory set passwords. Critical systems such as Healthcare and transportation can be jeopardized if hijacked. Using a bot, an attacker can use it to relinquish control from Smart city network administrators and users. In this paper, we present a Software-defined Deep learning based IoT Defense (SDID) mechanism which monitors and compares device historical traffic flow with current patterns to determine if a device is under an attack. Furthermore, to prevent false detection under flash-crowd events, the mechanism compares data with adjacent nodes to determine if the traffic flow is anomalous or not.

Original language	English
Title of host publication	Advanced Multimedia and Ubiquitous Engineering - MUE/FutureTech 2019
Editors	Laurence T. Yang, Fei Hao, James J. Park, Young-Sik Jeong
Publisher	Springer Verlag
Pages	239-242
Number of pages	4
ISBN (Print)	9789813292437
DOIs	https://doi.org/10.1007/978-981-32-9244-4_33
State	Published - 2020
Event	13th International Conference on Multimedia and Ubiquitous Engineering, MUE 2019 and 14th International Conference on Future Information Technology, Future Tech 2019 - Xian, China Duration: 24 Apr 2019 → 26 Apr 2019

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	590
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	13th International Conference on Multimedia and Ubiquitous Engineering, MUE 2019 and 14th International Conference on Future Information Technology, Future Tech 2019
Country/Territory	China
City	Xian
Period	24/04/19 → 26/04/19

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Keywords

Botnet
Cybersecurity
Deep Learning
Internet of Things
Smart city
Software defined networking

Access to Document

10.1007/978-981-32-9244-4_33

Cite this

Salim, M. M., & Park, J. H. (2020). Deep Learning Based IoT Re-authentication for Botnet Detection and Prevention. In L. T. Yang, F. Hao, J. J. Park, & Y.-S. Jeong (Eds.), Advanced Multimedia and Ubiquitous Engineering - MUE/FutureTech 2019 (pp. 239-242). (Lecture Notes in Electrical Engineering; Vol. 590). Springer Verlag. https://doi.org/10.1007/978-981-32-9244-4_33

@inproceedings{9c9bd6d1f7ae4182a822d9ed78bc7b10,

title = "Deep Learning Based IoT Re-authentication for Botnet Detection and Prevention",

abstract = "IoT devices face a grave security threat from botnet attacks. These devices are known for their poor default authentication system due to being set on weak factory set passwords. Critical systems such as Healthcare and transportation can be jeopardized if hijacked. Using a bot, an attacker can use it to relinquish control from Smart city network administrators and users. In this paper, we present a Software-defined Deep learning based IoT Defense (SDID) mechanism which monitors and compares device historical traffic flow with current patterns to determine if a device is under an attack. Furthermore, to prevent false detection under flash-crowd events, the mechanism compares data with adjacent nodes to determine if the traffic flow is anomalous or not.",

keywords = "Botnet, Cybersecurity, Deep Learning, Internet of Things, Smart city, Software defined networking",

author = "Salim, \{Mikail Mohammed\} and Park, \{Jong Hyuk\}",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Singapore Pte Ltd.; 13th International Conference on Multimedia and Ubiquitous Engineering, MUE 2019 and 14th International Conference on Future Information Technology, Future Tech 2019 ; Conference date: 24-04-2019 Through 26-04-2019",

year = "2020",

doi = "10.1007/978-981-32-9244-4\_33",

language = "English",

isbn = "9789813292437",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Verlag",

pages = "239--242",

editor = "Yang, \{Laurence T.\} and Fei Hao and Park, \{James J.\} and Young-Sik Jeong",

booktitle = "Advanced Multimedia and Ubiquitous Engineering - MUE/FutureTech 2019",

}

Salim, MM & Park, JH 2020, Deep Learning Based IoT Re-authentication for Botnet Detection and Prevention. in LT Yang, F Hao, JJ Park & Y-S Jeong (eds), Advanced Multimedia and Ubiquitous Engineering - MUE/FutureTech 2019. Lecture Notes in Electrical Engineering, vol. 590, Springer Verlag, pp. 239-242, 13th International Conference on Multimedia and Ubiquitous Engineering, MUE 2019 and 14th International Conference on Future Information Technology, Future Tech 2019, Xian, China, 24/04/19. https://doi.org/10.1007/978-981-32-9244-4_33

Deep Learning Based IoT Re-authentication for Botnet Detection and Prevention. / Salim, Mikail Mohammed; Park, Jong Hyuk.
Advanced Multimedia and Ubiquitous Engineering - MUE/FutureTech 2019. ed. / Laurence T. Yang; Fei Hao; James J. Park; Young-Sik Jeong. Springer Verlag, 2020. p. 239-242 (Lecture Notes in Electrical Engineering; Vol. 590).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep Learning Based IoT Re-authentication for Botnet Detection and Prevention

AU - Salim, Mikail Mohammed

AU - Park, Jong Hyuk

PY - 2020

Y1 - 2020

N2 - IoT devices face a grave security threat from botnet attacks. These devices are known for their poor default authentication system due to being set on weak factory set passwords. Critical systems such as Healthcare and transportation can be jeopardized if hijacked. Using a bot, an attacker can use it to relinquish control from Smart city network administrators and users. In this paper, we present a Software-defined Deep learning based IoT Defense (SDID) mechanism which monitors and compares device historical traffic flow with current patterns to determine if a device is under an attack. Furthermore, to prevent false detection under flash-crowd events, the mechanism compares data with adjacent nodes to determine if the traffic flow is anomalous or not.

AB - IoT devices face a grave security threat from botnet attacks. These devices are known for their poor default authentication system due to being set on weak factory set passwords. Critical systems such as Healthcare and transportation can be jeopardized if hijacked. Using a bot, an attacker can use it to relinquish control from Smart city network administrators and users. In this paper, we present a Software-defined Deep learning based IoT Defense (SDID) mechanism which monitors and compares device historical traffic flow with current patterns to determine if a device is under an attack. Furthermore, to prevent false detection under flash-crowd events, the mechanism compares data with adjacent nodes to determine if the traffic flow is anomalous or not.

KW - Botnet

KW - Cybersecurity

KW - Deep Learning

KW - Internet of Things

KW - Smart city

KW - Software defined networking

UR - https://www.scopus.com/pages/publications/85071837576

U2 - 10.1007/978-981-32-9244-4_33

DO - 10.1007/978-981-32-9244-4_33

M3 - Conference contribution

AN - SCOPUS:85071837576

SN - 9789813292437

T3 - Lecture Notes in Electrical Engineering

SP - 239

EP - 242

BT - Advanced Multimedia and Ubiquitous Engineering - MUE/FutureTech 2019

A2 - Yang, Laurence T.

A2 - Hao, Fei

A2 - Park, James J.

A2 - Jeong, Young-Sik

PB - Springer Verlag

T2 - 13th International Conference on Multimedia and Ubiquitous Engineering, MUE 2019 and 14th International Conference on Future Information Technology, Future Tech 2019

Y2 - 24 April 2019 through 26 April 2019

ER -

Deep Learning Based IoT Re-authentication for Botnet Detection and Prevention

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this