Securing Automotive Networks from DoS and Fuzzy Attacks with Optimized LSTM Models

Abstract Intelligently connected automobiles have come a long way thanks to the deep integration of cutting-edge networked gadgets and advancements in automotive technology. The increasing connectivity of vehicles has introduced significant cybersecurity concerns, particularly in controller area net...

Full description

Saved in:
Bibliographic Details
Main Authors: W. Beniel Dennyson, C. Jothikumar
Format: Article
Language:English
Published: Springer 2025-04-01
Series:International Journal of Computational Intelligence Systems
Subjects:
Online Access:https://doi.org/10.1007/s44196-025-00782-y
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849314724771004416
author W. Beniel Dennyson
C. Jothikumar
author_facet W. Beniel Dennyson
C. Jothikumar
author_sort W. Beniel Dennyson
collection DOAJ
description Abstract Intelligently connected automobiles have come a long way thanks to the deep integration of cutting-edge networked gadgets and advancements in automotive technology. The increasing connectivity of vehicles has introduced significant cybersecurity concerns, particularly in controller area network (CAN) bus systems, which are crucial for vehicle communication. For this, the research presents a novel hybrid model combining and integrating a long short-term memory (LSTM) neural network and bacterial foraging optimization (BFO) technique to address challenges like identifying fuzzy and denial of service (DoS) attacks on the CAN bus system. The model’s efficacy is demonstrated by evaluating various cyber-attacks from the Car-Hacking dataset. An adaptive feature selection method using BFO to identify optimal CAN bus characteristics for accurate attack detection. The LSTM-based temporal pattern recognition system detects anomalous message sequences and real-time countermeasures for mitigating DoS and fuzzy attacks. Reducing attack detection time to 0.0838 s, an enhancement over LSTM-AE, suggests improving detection speed. With a higher precision of 94.6% and F1-scores of 95.8%, LSTM-BFO outperforms other models based on accuracy, precision, and F1-score under the current experimental setup.
format Article
id doaj-art-ba8babdab8bd45e5aa6d78f12e8a235f
institution Kabale University
issn 1875-6883
language English
publishDate 2025-04-01
publisher Springer
record_format Article
series International Journal of Computational Intelligence Systems
spelling doaj-art-ba8babdab8bd45e5aa6d78f12e8a235f2025-08-20T03:52:23ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832025-04-0118112210.1007/s44196-025-00782-ySecuring Automotive Networks from DoS and Fuzzy Attacks with Optimized LSTM ModelsW. Beniel Dennyson0C. Jothikumar1Department of Computing Technologies, SRM Institute of Science and TechnologyDepartment of Computing Technologies, SRM Institute of Science and TechnologyAbstract Intelligently connected automobiles have come a long way thanks to the deep integration of cutting-edge networked gadgets and advancements in automotive technology. The increasing connectivity of vehicles has introduced significant cybersecurity concerns, particularly in controller area network (CAN) bus systems, which are crucial for vehicle communication. For this, the research presents a novel hybrid model combining and integrating a long short-term memory (LSTM) neural network and bacterial foraging optimization (BFO) technique to address challenges like identifying fuzzy and denial of service (DoS) attacks on the CAN bus system. The model’s efficacy is demonstrated by evaluating various cyber-attacks from the Car-Hacking dataset. An adaptive feature selection method using BFO to identify optimal CAN bus characteristics for accurate attack detection. The LSTM-based temporal pattern recognition system detects anomalous message sequences and real-time countermeasures for mitigating DoS and fuzzy attacks. Reducing attack detection time to 0.0838 s, an enhancement over LSTM-AE, suggests improving detection speed. With a higher precision of 94.6% and F1-scores of 95.8%, LSTM-BFO outperforms other models based on accuracy, precision, and F1-score under the current experimental setup.https://doi.org/10.1007/s44196-025-00782-yController area networkDeep learningDenial-of-serviceFuzzy attackAutomotive networkBacterial foraging optimization
spellingShingle W. Beniel Dennyson
C. Jothikumar
Securing Automotive Networks from DoS and Fuzzy Attacks with Optimized LSTM Models
International Journal of Computational Intelligence Systems
Controller area network
Deep learning
Denial-of-service
Fuzzy attack
Automotive network
Bacterial foraging optimization
title Securing Automotive Networks from DoS and Fuzzy Attacks with Optimized LSTM Models
title_full Securing Automotive Networks from DoS and Fuzzy Attacks with Optimized LSTM Models
title_fullStr Securing Automotive Networks from DoS and Fuzzy Attacks with Optimized LSTM Models
title_full_unstemmed Securing Automotive Networks from DoS and Fuzzy Attacks with Optimized LSTM Models
title_short Securing Automotive Networks from DoS and Fuzzy Attacks with Optimized LSTM Models
title_sort securing automotive networks from dos and fuzzy attacks with optimized lstm models
topic Controller area network
Deep learning
Denial-of-service
Fuzzy attack
Automotive network
Bacterial foraging optimization
url https://doi.org/10.1007/s44196-025-00782-y
work_keys_str_mv AT wbenieldennyson securingautomotivenetworksfromdosandfuzzyattackswithoptimizedlstmmodels
AT cjothikumar securingautomotivenetworksfromdosandfuzzyattackswithoptimizedlstmmodels