Adversarial Attacks on Cognitive Self-Organizing Networks: The Challenge and the Way Forward

Abstract--Future communications and data networks are expected to be largely cognitive self-organizing networks (CSON). Such networks will have the essential property of cognitive selforganization, which can be achieved using machine learning techniques (e.g., deep learning). Despite the potential of these techniques, these techniques in their current form are vulnerable to adversarial attacks that can cause cascaded damages with detrimental consequences for the whole network. In this paper, we explore the effect of adversarial attacks on CSON. Our experiments highlight the level of threat that CSON have to deal with in order to meet the challenges of next-generation networks and point out promising directions for future work. The idea that networks should learn to drive themselves is gaining traction [11], taking inspiration from self-driving cars where driving and related functionality do not require human intervention. The networking community wants to build a similar cognitive control in networks where networks are able to configure, manage, and protect themselves by interacting with the dynamic networking environment.We refer to such networks as cognitive self-organizing networks CSON. The expected complexity and heterogeneity of CSON makes machine learning (ML) a reasonable choice for realizing this ambitious goal. Recently artificial intelligence (AI) based CSON have attained a lot of attention in industry and academia.