Adversarial Attack of ML-based Intrusion Detection System on In-vehicle System using GAN

Eun Seong Seo; Jeong Eun Kim; Wook Lee; Junhee Seok

doi:10.1109/ICUFN57995.2023.10200297

Adversarial Attack of ML-based Intrusion Detection System on In-vehicle System using GAN

Eun Seong Seo, Jeong Eun Kim, Wook Lee, Junhee Seok

School of Electrical Engineering

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

1 Citation (Scopus)

Abstract

In recent years, research has focused on developing intrusion detection systems (IDS) within vehicle networks to prevent automotive hacking from external cyberattacks. While machine learning (ML) techniques have shown promise in detecting known attacks, their vulnerability to adversarial examples remains a significant challenge. In this study, we introduce a Generative Adversarial Network (GAN)-based method for creating adversarial attacks capable of bypassing ML-based IDS in in-vehicle networks. Our approach involves preprocessing an automotive hacking dataset, training a GAN-based model, and evaluating the generated attacks using accuracy metrics. The results demonstrate that adversarial attacks effectively reduce the detection accuracy of various IDSs to less than 50%, emphasizing the importance of addressing adversarial cases when designing and evaluating ML-based IDSs for in-vehicle networks. Additionally, t-SNE visualization reveals the successful generation of new adversarial attacks, highlighting the need for ongoing research to strengthen the security of in-vehicle systems.

Original language	English
Title of host publication	ICUFN 2023 - 14th International Conference on Ubiquitous and Future Networks
Publisher	IEEE Computer Society
Pages	700-703
Number of pages	4
ISBN (Electronic)	9798350335385
DOIs	https://doi.org/10.1109/ICUFN57995.2023.10200297
Publication status	Published - 2023
Event	14th International Conference on Ubiquitous and Future Networks, ICUFN 2023 - Paris, France Duration: 2023 Jul 4 → 2023 Jul 7

Publication series

Name	International Conference on Ubiquitous and Future Networks, ICUFN
Volume	2023-July
ISSN (Print)	2165-8528
ISSN (Electronic)	2165-8536

Conference

Conference	14th International Conference on Ubiquitous and Future Networks, ICUFN 2023
Country/Territory	France
City	Paris
Period	23/7/4 → 23/7/7

Bibliographical note

Funding Information:
This work was supported by a grant from the National Research Foundation of Korea (NRF-2022R1A2C2004003)

Publisher Copyright:
© 2023 IEEE.

Keywords

Adversarial attack
GAN
In-vehicle networks
Intrusion detection system
Machine Learning

ASJC Scopus subject areas

Computer Networks and Communications
Computer Science Applications
Hardware and Architecture

Access to Document

10.1109/ICUFN57995.2023.10200297

Cite this

Seo, E. S., Kim, J. E., Lee, W., & Seok, J. (2023). Adversarial Attack of ML-based Intrusion Detection System on In-vehicle System using GAN. In ICUFN 2023 - 14th International Conference on Ubiquitous and Future Networks (pp. 700-703). (International Conference on Ubiquitous and Future Networks, ICUFN; Vol. 2023-July). IEEE Computer Society. https://doi.org/10.1109/ICUFN57995.2023.10200297

Adversarial Attack of ML-based Intrusion Detection System on In-vehicle System using GAN. / Seo, Eun Seong; Kim, Jeong Eun; Lee, Wook et al.
ICUFN 2023 - 14th International Conference on Ubiquitous and Future Networks. IEEE Computer Society, 2023. p. 700-703 (International Conference on Ubiquitous and Future Networks, ICUFN; Vol. 2023-July).

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

Seo, ES, Kim, JE, Lee, W & Seok, J 2023, Adversarial Attack of ML-based Intrusion Detection System on In-vehicle System using GAN. in ICUFN 2023 - 14th International Conference on Ubiquitous and Future Networks. International Conference on Ubiquitous and Future Networks, ICUFN, vol. 2023-July, IEEE Computer Society, pp. 700-703, 14th International Conference on Ubiquitous and Future Networks, ICUFN 2023, Paris, France, 23/7/4. https://doi.org/10.1109/ICUFN57995.2023.10200297

@inproceedings{953518a956c744abaddcda7574c73186,

title = "Adversarial Attack of ML-based Intrusion Detection System on In-vehicle System using GAN",

abstract = "In recent years, research has focused on developing intrusion detection systems (IDS) within vehicle networks to prevent automotive hacking from external cyberattacks. While machine learning (ML) techniques have shown promise in detecting known attacks, their vulnerability to adversarial examples remains a significant challenge. In this study, we introduce a Generative Adversarial Network (GAN)-based method for creating adversarial attacks capable of bypassing ML-based IDS in in-vehicle networks. Our approach involves preprocessing an automotive hacking dataset, training a GAN-based model, and evaluating the generated attacks using accuracy metrics. The results demonstrate that adversarial attacks effectively reduce the detection accuracy of various IDSs to less than 50%, emphasizing the importance of addressing adversarial cases when designing and evaluating ML-based IDSs for in-vehicle networks. Additionally, t-SNE visualization reveals the successful generation of new adversarial attacks, highlighting the need for ongoing research to strengthen the security of in-vehicle systems.",

keywords = "Adversarial attack, GAN, In-vehicle networks, Intrusion detection system, Machine Learning",

author = "Seo, {Eun Seong} and Kim, {Jeong Eun} and Wook Lee and Junhee Seok",

note = "Funding Information: This work was supported by a grant from the National Research Foundation of Korea (NRF-2022R1A2C2004003) Publisher Copyright: {\textcopyright} 2023 IEEE.; 14th International Conference on Ubiquitous and Future Networks, ICUFN 2023 ; Conference date: 04-07-2023 Through 07-07-2023",

year = "2023",

doi = "10.1109/ICUFN57995.2023.10200297",

language = "English",

series = "International Conference on Ubiquitous and Future Networks, ICUFN",

publisher = "IEEE Computer Society",

pages = "700--703",

booktitle = "ICUFN 2023 - 14th International Conference on Ubiquitous and Future Networks",

}

TY - GEN

T1 - Adversarial Attack of ML-based Intrusion Detection System on In-vehicle System using GAN

AU - Seo, Eun Seong

AU - Kim, Jeong Eun

AU - Lee, Wook

AU - Seok, Junhee

PY - 2023

Y1 - 2023

N2 - In recent years, research has focused on developing intrusion detection systems (IDS) within vehicle networks to prevent automotive hacking from external cyberattacks. While machine learning (ML) techniques have shown promise in detecting known attacks, their vulnerability to adversarial examples remains a significant challenge. In this study, we introduce a Generative Adversarial Network (GAN)-based method for creating adversarial attacks capable of bypassing ML-based IDS in in-vehicle networks. Our approach involves preprocessing an automotive hacking dataset, training a GAN-based model, and evaluating the generated attacks using accuracy metrics. The results demonstrate that adversarial attacks effectively reduce the detection accuracy of various IDSs to less than 50%, emphasizing the importance of addressing adversarial cases when designing and evaluating ML-based IDSs for in-vehicle networks. Additionally, t-SNE visualization reveals the successful generation of new adversarial attacks, highlighting the need for ongoing research to strengthen the security of in-vehicle systems.

AB - In recent years, research has focused on developing intrusion detection systems (IDS) within vehicle networks to prevent automotive hacking from external cyberattacks. While machine learning (ML) techniques have shown promise in detecting known attacks, their vulnerability to adversarial examples remains a significant challenge. In this study, we introduce a Generative Adversarial Network (GAN)-based method for creating adversarial attacks capable of bypassing ML-based IDS in in-vehicle networks. Our approach involves preprocessing an automotive hacking dataset, training a GAN-based model, and evaluating the generated attacks using accuracy metrics. The results demonstrate that adversarial attacks effectively reduce the detection accuracy of various IDSs to less than 50%, emphasizing the importance of addressing adversarial cases when designing and evaluating ML-based IDSs for in-vehicle networks. Additionally, t-SNE visualization reveals the successful generation of new adversarial attacks, highlighting the need for ongoing research to strengthen the security of in-vehicle systems.

KW - Adversarial attack

KW - GAN

KW - In-vehicle networks

KW - Intrusion detection system

KW - Machine Learning

UR - http://www.scopus.com/inward/record.url?scp=85169300120&partnerID=8YFLogxK

U2 - 10.1109/ICUFN57995.2023.10200297

DO - 10.1109/ICUFN57995.2023.10200297

M3 - Conference contribution

AN - SCOPUS:85169300120

T3 - International Conference on Ubiquitous and Future Networks, ICUFN

SP - 700

EP - 703

BT - ICUFN 2023 - 14th International Conference on Ubiquitous and Future Networks

PB - IEEE Computer Society

T2 - 14th International Conference on Ubiquitous and Future Networks, ICUFN 2023

Y2 - 4 July 2023 through 7 July 2023

ER -

Adversarial Attack of ML-based Intrusion Detection System on In-vehicle System using GAN

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this