Integrated Sensing and Communications Using Generative AI: Countering Adversarial Machine Learning Attacks

In the field of Integrated Sensing and Commu-nication (ISAC) systems, several challenges emerge, such as obtaining the infinitesimal Cramer-Ran lower bound (CRLB) for sensing outcomes and addressing the vulnerabilities of ISAC to adversarial machine learning (AML) attacks. To address this, we propose a Smart ISAC (S-ISAC) system, which incorporates a unique generative adversarial network (GAN) combined with a differentiable Kolmogorov-Smirnov (KS) loss function, named KSGAN. This KSGAN is tailor-made to identify AML attacks on range-Doppler heatmap features. Only after ensuring that the range-Doppler heatmap is free from AML attacks using KSGAN, do we apply the Constant False Alarm Rate (CFAR) for accurate estimation of target vehicle parameters. We implement a rigorous ISAC system under AML attacks using Matlab Toolboxes and the adversarial robustness toolbox (ART). Our numerical findings indicate that the proposed KSGAN offers greater accuracy in detecting AML than a standalone GAN. Additionally, our results show that the MIMO S-ISAC Beamforming surpasses the performance of the standalone ISAC system.