Siamese network based feature learning for improved intrusion detection

Houda Jmila 1, 2, 3 Mohamed Ibn Khedher 4 Gregory Blanc 1, 2, 3 Mounim El Yacoubi 5, 2, 6
3 R3S-SAMOVAR - Réseaux, Systèmes, Services, Sécurité
SAMOVAR - Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux
6 ARMEDIA-SAMOVAR - ARMEDIA
SAMOVAR - Services répartis, Architectures, MOdélisation, Validation, Administration des Réseaux
Abstract : Intrusion detection is a critical Cyber Security subject. Different Machine Learning (ML) approaches have been proposed for Intrusion Detection Systems (IDS). However, their application to real-life scenarios remains challenging due to high data dimensionality. Representation learning (RL) allows discriminative feature representation in a low dimensionality space. The application of this technique in IDS requires more investigation. This paper examines and discusses the contribution of Siamese network based representation learning in improving the IDS performance. Extensive experimental results under different evaluation scenarios show different improvement rates depending on the scenario.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02421070
Contributor : Mohamed Ibn Khedher <>
Submitted on : Friday, December 20, 2019 - 11:36:16 AM
Last modification on : Tuesday, February 18, 2020 - 12:04:08 PM

Identifiers

Citation

Houda Jmila, Mohamed Ibn Khedher, Gregory Blanc, Mounim El Yacoubi. Siamese network based feature learning for improved intrusion detection. ICONIP 2019: International Conference on Neural Information Processing, Dec 2019, Sydney, Australia. pp.377-389, ⟨10.1007/978-3-030-36708-4_31⟩. ⟨hal-02421070⟩

Share

Metrics

Record views

28