Deep Learning-Based Intrusion Detection With Adversaries

• Published in: IEEE access Vol. 6; pp. 38367 - 38384
• Main Author: Wang, Zheng
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2018; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; classification algorithms; Cognitive tasks; data security; Deep learning; Feature extraction; Image classification; Intrusion detection; Intrusion detection systems; Machine learning; Measurement; Neural networks; Perturbation methods; Security management; Task analysis; NSL-KDD dataset; intrusion detection; deep neural networks; adversarial examples

Deep neural networks have demonstrated their effectiveness in most machine learning tasks, with intrusion detection included. Unfortunately, recent research found that deep neural networks are vulnerable to adversarial examples in the image classification domain, i.e., they leave some opportunities...