Adversarial Attack Detection Approach for Intrusion Detection Systems

DEĞİRMENCİ E., ÖZÇELİK İ., YAZICI A.

IEEE Access, vol.12, pp.195996-196009, 2024 (SCI-Expanded) identifier

  • Publication Type: Article / Article
  • Volume: 12
  • Publication Date: 2024
  • Doi Number: 10.1109/access.2024.3520406
  • Journal Name: IEEE Access
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, INSPEC, Directory of Open Access Journals
  • Page Numbers: pp.195996-196009
  • Keywords: Adversarial attacks, deep learning, intrusion detection systems, machine learning resilience, reconstruction error, security
  • Eskisehir Osmangazi University Affiliated: Yes

Abstract

The adoption of deep learning has exposed significant vulnerabilities, especially to adversarial attacks that cause misclassifications through subtle small perturbations. Such attacks challenge security-critical applications. This study addresses these vulnerabilities by proposing a novel adversarial attack detection method leveraging data reconstruction errors. We evaluate this approach against three well-known adversarial attacks - Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), and Basic Iterative Method (BIM) - on Intrusion Detection Systems. Our method combines reconstruction error alongside aleatoric, epistemic, and entropy metrics to distinguish between original and adversarial samples. Experimental results show that our approach achieves a detection success rate of 92% to 100%, outperforming existing methods, particularly at low perturbation levels. This research enhances the robustness and reliability of machine learning models against adversarial threats by using effective error metrics in adversarial detection.