Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Adversarial Attacks Against Double RIS-Assisted MIMO Systems-based Autoencoder in Finite-Scattering Environments

Bui Duc Son, Ngo Nam Khanh, Trinh Van Chien, Dong In Kim

TL;DR

This letter explores adversarial attacks against a double reconfigurable intelligent surface (RIS)-assisted multiple-input and multiple-output (MIMO)-based autoencoder, where an adversary employs encoded and decoded datasets to create adversarial perturbation and fool the system.

Abstract

Autoencoder permits the end-to-end optimization and design of wireless communication systems to be more beneficial than traditional signal processing. However, this emerging learning-based framework has weaknesses, especially sensitivity to physical attacks. This paper explores adversarial attacks against a double reconfigurable intelligent surface (RIS)-assisted multiple-input and multiple-output (MIMO)-based autoencoder, where an adversary employs encoded and decoded datasets to create adversarial perturbation and fool the system. Because of the complex and dynamic data structures, adversarial attacks are not unique, each having its own benefits. We, therefore, propose three algorithms generating adversarial examples and perturbations to attack the RIS-MIMO-based autoencoder, exploiting the gradient descent and allowing for flexibility via varying the input dimensions. Numerical results show that the proposed adversarial attack-based algorithm significantly degrades the system performance regarding the symbol error rate compared to the jamming attacks.

Adversarial Attacks Against Double RIS-Assisted MIMO Systems-based Autoencoder in Finite-Scattering Environments

TL;DR

This letter explores adversarial attacks against a double reconfigurable intelligent surface (RIS)-assisted multiple-input and multiple-output (MIMO)-based autoencoder, where an adversary employs encoded and decoded datasets to create adversarial perturbation and fool the system.

Abstract

Autoencoder permits the end-to-end optimization and design of wireless communication systems to be more beneficial than traditional signal processing. However, this emerging learning-based framework has weaknesses, especially sensitivity to physical attacks. This paper explores adversarial attacks against a double reconfigurable intelligent surface (RIS)-assisted multiple-input and multiple-output (MIMO)-based autoencoder, where an adversary employs encoded and decoded datasets to create adversarial perturbation and fool the system. Because of the complex and dynamic data structures, adversarial attacks are not unique, each having its own benefits. We, therefore, propose three algorithms generating adversarial examples and perturbations to attack the RIS-MIMO-based autoencoder, exploiting the gradient descent and allowing for flexibility via varying the input dimensions. Numerical results show that the proposed adversarial attack-based algorithm significantly degrades the system performance regarding the symbol error rate compared to the jamming attacks.

Paper Structure

This paper contains 10 sections, 10 equations, 2 figures, 1 algorithm.

Table of Contents

  1. INTRODUCTION
  2. SYSTEM MODEL
  3. Double scattering fading channels
  4. Encoder
  5. RIS 1 and RIS 2
  6. Decoder
  7. Adversary
  8. Adversarial attack
  9. Numerical results
  10. Conclusion

Figures (2)

  • Figure 1: (a) The communication model under the adversarial attack. (b) The considered communication model from the top view.
  • Figure 2: (a) The SER of the four considered benchmarks when the number of scatterers is 9 under the ideal attacking channel. (b) The SER of RMAEP with the different number of scatterers under the ideal attacking channel. (c) Comparing the SER between RMAEP and RMAEF with the different numbers of scatterers under the ideal attacking channel. (d) Comparing the SER of RMAEP under ideal attacking and double-scattering channels.