English

Universal Adversarial Attacks on Neural Networks for Power Allocation in a Massive MIMO System

Information Theory 2021-10-12 v1 Cryptography and Security Machine Learning math.IT

Abstract

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.

Keywords

Cite

@article{arxiv.2110.04731,
  title  = {Universal Adversarial Attacks on Neural Networks for Power Allocation in a Massive MIMO System},
  author = {Pablo Millán Santos and B. R. Manoj and Meysam Sadeghi and Erik G. Larsson},
  journal= {arXiv preprint arXiv:2110.04731},
  year   = {2021}
}

Comments

accepted for publication in IEEE Wireless Communications Letters

R2 v1 2026-06-24T06:46:08.885Z