Assessing adversarial training effect on IDSs and GANs - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Assessing adversarial training effect on IDSs and GANs

Résumé

Deep neural network-based Intrusion Detection Systems (IDSs) are gaining popularity to improve anomaly detection accuracy and robustness. Yet, Deep neural network (DNN) models have been shown to be vulnerable to adversarial attacks. An attacker can use a generator, here a Generative Adversarial Network, to alter an attack so that the IDS model misclassify it as normal network traffic. There is a race between adversarial attacks and mechanisms to make robust IDSs, like Adversarial Training. To our knowledge, no study thoroughly assesses how attack generators or IDS training is sensitive to parameters controlling resources spent during training. Such results provide insights on how much to spend on IDS training. This paper presents the outcome of this assessment for GANs vs adversarial training. Interestingly, it shows that GANs' evasion capabilities are either very good or poor, with almost no average cases. Resources impact the likelihood of obtaining an efficient generator.
Fichier non déposé

Dates et versions

hal-03775550 , version 1 (12-09-2022)

Identifiants

Citer

Hassan Chaitou, Thomas Robert, Jean Leneutre, Laurent Pautet. Assessing adversarial training effect on IDSs and GANs. 2021 IEEE International Conference on Cyber Security and Resilience (CSR) Workshop on Resilient Artificial Intelligence, Jul 2021, Rhodes, France. pp.543-550, ⟨10.1109/CSR51186.2021.9527949⟩. ⟨hal-03775550⟩
32 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More