# The Best Defense Is a Good Offense: Adversarial Attacks to Avoid Modulation Detection

## TL;DR

This paper introduces a method to enhance wireless communication security by perturbing signals to deceive intruders attempting to identify modulation schemes, while ensuring reliable message decoding by the legitimate receiver.

## Contribution

It proposes a novel adversarial perturbation technique for wireless signals that reduces intruder detection accuracy without compromising legitimate communication.

## Key findings

- Effective perturbation reduces intruder accuracy significantly.
- Diverse training data and curriculum learning improve intruder detection.
- Method maintains high communication reliability for legitimate receiver.

## Abstract

We consider a communication scenario, in which an intruder tries to determine the modulation scheme of the intercepted signal. Our aim is to minimize the accuracy of the intruder, while guaranteeing that the intended receiver can still recover the underlying message with the highest reliability. This is achieved by perturbing channel input symbols at the encoder, similarly to adversarial attacks against classifiers in machine learning. In image classification, the perturbation is limited to be imperceptible to a human observer, while in our case the perturbation is constrained so that the message can still be reliably decoded by the legitimate receiver, which is oblivious to the perturbation. Simulation results demonstrate the viability of our approach to make wireless communication secure against state-of-the-art intruders (using deep learning or decision trees) with minimal sacrifice in the communication performance. On the other hand, we also demonstrate that using diverse training data and curriculum learning can significantly boost the accuracy of the intruder.