{"id":{"repo_id":"ets-quebec","oai_identifier":"oai:espace.etsmtl.ca:3333"},"canonical_url":"https://search.ndltd.org/etd/ets-quebec/oai:espace.etsmtl.ca:3333","repository":{"repo_id":"ets-quebec","name":"ETS (Quebec)","base_url":"https://espace.etsmtl.ca/cgi/oai2"},"display":{"title":"Enhancing intrusion detection in vehicular networks through deep learning approaches","abstract":"The recent expansion of the Internet of Things (IoT) has transformed vehicular networks into the Internet of Vehicles (IoV), where modern vehicles are exposed to various new types of cyber-attacks. In order to address these vulnerabilities, Intrusion Detection Systems (IDS) play a crucial role by effectively identifying and detecting attacks with a high level of accuracy while minimizing false alarms. Traditional Machine Learning (ML) approaches have been utilized to identify intruders in the network. However, they often suffer from low detection accuracy and high complexity, making them ill-suited for dynamic attacks. Therefore, there is a need for an advanced IDS suitable for real-time scenarios. To enhance the security of IoV, we propose a novel IDS based on a generative hybrid deep learning (DL) model. The proposed model combines the Long Short-Term Memory Variational AutoEncoder (LSTMVAE), Bidirectional Gated Recurrent Units (BiGRU), and a softmax classifier. The LSTMVAE is employed as a statistical feature extraction technique capable of learning time series and multivariate data from the IoV network. The extracted features are then fed into the BiGRU and softmax classifier for the identification and classification of potential cyber-attacks in the IoV network. Experimental results based on the ToN-IoT dataset validate the superior performance of the proposed IDS over commonly used baseline techniques. By leveraging the strengths of DL and generative models, the proposed IDS offers a more effective solution for attack detection in IoV networks. It addresses the limitations of traditional ML approaches and demonstrates improved accuracy and performance in identifying and classifying cyber-attacks. This research contributes to enhancing the security of IoV systems and mitigating the risks associated with the emerging threats.","abstract_html":"The recent expansion of the Internet of Things (IoT) has transformed vehicular networks into the Internet of Vehicles (IoV), where modern vehicles are exposed to various new types of cyber-attacks. In order to address these vulnerabilities, Intrusion Detection Systems (IDS) play a crucial role by effectively identifying and detecting attacks with a high level of accuracy while minimizing false alarms. Traditional Machine Learning (ML) approaches have been utilized to identify intruders in the network. However, they often suffer from low detection accuracy and high complexity, making them ill-suited for dynamic attacks. Therefore, there is a need for an advanced IDS suitable for real-time scenarios. To enhance the security of IoV, we propose a novel IDS based on a generative hybrid deep learning (DL) model. The proposed model combines the Long Short-Term Memory Variational AutoEncoder (LSTMVAE), Bidirectional Gated Recurrent Units (BiGRU), and a softmax classifier. The LSTMVAE is employed as a statistical feature extraction technique capable of learning time series and multivariate data from the IoV network. The extracted features are then fed into the BiGRU and softmax classifier for the identification and classification of potential cyber-attacks in the IoV network. Experimental results based on the ToN-IoT dataset validate the superior performance of the proposed IDS over commonly used baseline techniques. By leveraging the strengths of DL and generative models, the proposed IDS offers a more effective solution for attack detection in IoV networks. It addresses the limitations of traditional ML approaches and demonstrates improved accuracy and performance in identifying and classifying cyber-attacks. This research contributes to enhancing the security of IoV systems and mitigating the risks associated with the emerging threats.","abstract_has_math":false,"creators":["Aggarwal, Kanika"],"institution":"École de technologie supérieure","degree_name":"Mémoire de maîtrise électronique","degree_level":"masters","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023-09-16","date_published":"2023-09-16","updated_at":"2026-11-18T22:10:08Z","subjects":["système de détection d’intrusion, Internet des véhicules (IoV), sécurité, mémoire longue à court terme, apprentissage en profondeur"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["INSERT-YOUR-LIBRARY-ID-HERE3333"],"render_values":[{"text":"INSERT-YOUR-LIBRARY-ID-HERE3333","href":null,"code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null,"record_url":null,"record_label":null,"record_kind":null,"record_source":null,"download_url":"https://espace.etsmtl.ca/id/eprint/3333/1/AGGARWAL_Kanika.pdf","download_label":"Download PDF","download_source":"dc:identifier","access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://espace.etsmtl.ca/cgi/oai2?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Aespace.etsmtl.ca%3A3333","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Aggarwal, Kanika"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2023-09-16"]},{"key":"dc:publisher","label":"Institution","values":["École de technologie supérieure"]},{"key":"dc:type","label":"Dc Type","values":["Electronic Thesis or Dissertation"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Mémoire de maîtrise électronique"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["École de technologie supérieure"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["système de détection d’intrusion, Internet des véhicules (IoV), sécurité, mémoire longue à court terme, apprentissage en profondeur"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["INSERT-YOUR-LIBRARY-ID-HERE3333","https://espace.etsmtl.ca/id/eprint/3333/1/AGGARWAL_Kanika.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The recent expansion of the Internet of Things (IoT) has transformed vehicular networks into the Internet of Vehicles (IoV), where modern vehicles are exposed to various new types of cyber-attacks. In order to address these vulnerabilities, Intrusion Detection Systems (IDS) play a crucial role by effectively identifying and detecting attacks with a high level of accuracy while minimizing false alarms. Traditional Machine Learning (ML) approaches have been utilized to identify intruders in the network. However, they often suffer from low detection accuracy and high complexity, making them ill-suited for dynamic attacks. Therefore, there is a need for an advanced IDS suitable for real-time scenarios. To enhance the security of IoV, we propose a novel IDS based on a generative hybrid deep learning (DL) model. The proposed model combines the Long Short-Term Memory Variational AutoEncoder (LSTMVAE), Bidirectional Gated Recurrent Units (BiGRU), and a softmax classifier. The LSTMVAE is employed as a statistical feature extraction technique capable of learning time series and multivariate data from the IoV network. The extracted features are then fed into the BiGRU and softmax classifier for the identification and classification of potential cyber-attacks in the IoV network. Experimental results based on the ToN-IoT dataset validate the superior performance of the proposed IDS over commonly used baseline techniques. By leveraging the strengths of DL and generative models, the proposed IDS offers a more effective solution for attack detection in IoV networks. It addresses the limitations of traditional ML approaches and demonstrates improved accuracy and performance in identifying and classifying cyber-attacks. This research contributes to enhancing the security of IoV systems and mitigating the risks associated with the emerging threats."]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Enhancing intrusion detection in vehicular networks through deep learning approaches"]}]}],"canonical_facts":{"dc:creator":["Aggarwal, Kanika"],"dc:date":["2023-09-16"],"dc:description":["The recent expansion of the Internet of Things (IoT) has transformed vehicular networks into the Internet of Vehicles (IoV), where modern vehicles are exposed to various new types of cyber-attacks. In order to address these vulnerabilities, Intrusion Detection Systems (IDS) play a crucial role by effectively identifying and detecting attacks with a high level of accuracy while minimizing false alarms. Traditional Machine Learning (ML) approaches have been utilized to identify intruders in the network. However, they often suffer from low detection accuracy and high complexity, making them ill-suited for dynamic attacks. Therefore, there is a need for an advanced IDS suitable for real-time scenarios. To enhance the security of IoV, we propose a novel IDS based on a generative hybrid deep learning (DL) model. The proposed model combines the Long Short-Term Memory Variational AutoEncoder (LSTMVAE), Bidirectional Gated Recurrent Units (BiGRU), and a softmax classifier. The LSTMVAE is employed as a statistical feature extraction technique capable of learning time series and multivariate data from the IoV network. The extracted features are then fed into the BiGRU and softmax classifier for the identification and classification of potential cyber-attacks in the IoV network. Experimental results based on the ToN-IoT dataset validate the superior performance of the proposed IDS over commonly used baseline techniques. By leveraging the strengths of DL and generative models, the proposed IDS offers a more effective solution for attack detection in IoV networks. It addresses the limitations of traditional ML approaches and demonstrates improved accuracy and performance in identifying and classifying cyber-attacks. This research contributes to enhancing the security of IoV systems and mitigating the risks associated with the emerging threats."],"dc:format":["application/pdf"],"dc:identifier":["INSERT-YOUR-LIBRARY-ID-HERE3333","https://espace.etsmtl.ca/id/eprint/3333/1/AGGARWAL_Kanika.pdf"],"dc:language":["en"],"dc:publisher":["École de technologie supérieure"],"dc:subject":["système de détection d’intrusion, Internet des véhicules (IoV), sécurité, mémoire longue à court terme, apprentissage en profondeur"],"dc:title":["Enhancing intrusion detection in vehicular networks through deep learning approaches"],"dc:type":["Electronic Thesis or Dissertation"],"thesis:degree_level":["masters"],"thesis:degree_name":["Mémoire de maîtrise électronique"],"thesis:institution_name":["École de technologie supérieure"]},"updated_at":"2026-11-18T22:10:08Z"}