The micro-Doppler Attack Against AI-based Human Activity Classification from Wireless Signals

TL;DR

This paper introduces a micro-Doppler attack on AI-based human activity classification systems that use wireless signals, demonstrating how waveform manipulation can drastically reduce classification accuracy.

Contribution

The paper presents a novel micro-Doppler attack method targeting wireless OFDM signals used in HAC systems, showing its effectiveness in deceiving AI classifiers.

Findings

HAC accuracy drops below 10% under attack

Waveform manipulation alters micro-Doppler signatures

Effective attack demonstrated on CNN-based classifiers

Abstract

A subset of Human Activity Classification (HAC) systems are based on AI algorithms that use passively collected wireless signals. This paper presents the micro-Doppler attack targeting HAC from wireless orthogonal frequency division multiplexing (OFDM) signals. The attack is executed by inserting artificial variations in a transmitted OFDM waveform to alter its micro-Doppler signature when it reflects off a human target. We investigate two variants of our scheme that manipulate the waveform at different time scales resulting in altered receiver spectrograms. HAC accuracy with a deep convolutional neural network (CNN) can be reduced to less than 10%.