TY - JOUR
T1 - Collaborative Intrusion Detection for VANETs
T2 - A Deep Learning-Based Distributed SDN Approach
AU - Shu, Jiangang
AU - Zhou, Lei
AU - Zhang, Weizhe
AU - Du, Xiaojiang
AU - Guizani, Mohsen
N1 - Publisher Copyright:
© 2000-2011 IEEE.
PY - 2021/7
Y1 - 2021/7
N2 - Vehicular Ad hoc Network (VANET) is an enabling technology to provide a variety of convenient services in intelligent transportation systems, and yet vulnerable to various intrusion attacks. Intrusion detection systems (IDSs) can mitigate the security threats by detecting abnormal network behaviours. However, existing IDS solutions are limited to detect abnormal network behaviors under local sub-networks rather than the entire VANET. To address this problem, we utilize deep learning with generative adversarial networks and explore distributed SDN to design a collaborative intrusion detection system (CIDS) for VANETs, which enables multiple SDN controllers jointly train a global intrusion detection model for the entire network without directly exchanging their sub-network flows. We prove the correctness of our CIDS in both IID (Independent Identically Distribution) and non-IID situations, and also evaluate its performance through both theoretical analysis and experimental evaluation on a real-world dataset. Detailed experimental results validate that our CIDS is efficient and effective in intrusion detection for VANETs.
AB - Vehicular Ad hoc Network (VANET) is an enabling technology to provide a variety of convenient services in intelligent transportation systems, and yet vulnerable to various intrusion attacks. Intrusion detection systems (IDSs) can mitigate the security threats by detecting abnormal network behaviours. However, existing IDS solutions are limited to detect abnormal network behaviors under local sub-networks rather than the entire VANET. To address this problem, we utilize deep learning with generative adversarial networks and explore distributed SDN to design a collaborative intrusion detection system (CIDS) for VANETs, which enables multiple SDN controllers jointly train a global intrusion detection model for the entire network without directly exchanging their sub-network flows. We prove the correctness of our CIDS in both IID (Independent Identically Distribution) and non-IID situations, and also evaluate its performance through both theoretical analysis and experimental evaluation on a real-world dataset. Detailed experimental results validate that our CIDS is efficient and effective in intrusion detection for VANETs.
KW - Collaborative intrusion detection
KW - deep learning
KW - distributed SDN
KW - generative adversarial networks
KW - intelligent transportation
UR - http://www.scopus.com/inward/record.url?scp=85110641244&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85110641244&partnerID=8YFLogxK
U2 - 10.1109/TITS.2020.3027390
DO - 10.1109/TITS.2020.3027390
M3 - Article
AN - SCOPUS:85110641244
SN - 1524-9050
VL - 22
SP - 4519
EP - 4530
JO - IEEE Transactions on Intelligent Transportation Systems
JF - IEEE Transactions on Intelligent Transportation Systems
IS - 7
M1 - 9216536
ER -