Universal Adversarial Attacks on Neural Networks for Power Allocation in a Massive MIMO System
This addresses security risks in wireless communication systems, though it is incremental as it adapts known adversarial attack techniques to a specific domain.
The paper tackled the vulnerability of deep learning models for power allocation in massive MIMO systems by proposing universal adversarial perturbation methods, achieving adversarial success rates of up to 60% for white-box and 40% for black-box attacks.
Deep learning (DL) architectures have been successfully used in many applications including wireless systems. However, they have been shown to be susceptible to adversarial attacks. We analyze DL-based models for a regression problem in the context of downlink power allocation in massive multiple-input-multiple-output systems and propose universal adversarial perturbation (UAP)-crafting methods as white-box and black-box attacks. We benchmark the UAP performance of white-box and black-box attacks for the considered application and show that the adversarial success rate can achieve up to 60% and 40%, respectively. The proposed UAP-based attacks make a more practical and realistic approach as compared to classical white-box attacks.