# Imperio: Robust Over-the-Air Adversarial Examples for Automatic Speech Recognition Systems

## TL;DR

This paper introduces a novel algorithm for generating robust over-the-air adversarial audio examples that are effective across different room environments without prior room knowledge, leveraging room impulse responses and psychoacoustic hiding techniques.

## Contribution

The authors present the first generic over-the-air adversarial example generation method that is robust to room variations and does not require environment-specific adjustments.

## Key findings

- Adversarial examples remain effective across various room configurations.
- No line-of-sight between speaker and microphone is necessary for successful attacks.
- Psychoacoustic methods can hide adversarial perturbations below human hearing thresholds.

## Abstract

Automatic speech recognition (ASR) systems can be fooled via targeted adversarial examples, which induce the ASR to produce arbitrary transcriptions in response to altered audio signals. However, state-of-the-art adversarial examples typically have to be fed into the ASR system directly, and are not successful when played in a room. The few published over-the-air adversarial examples fall into one of three categories: they are either handcrafted examples, they are so conspicuous that human listeners can easily recognize the target transcription once they are alerted to its content, or they require precise information about the room where the attack takes place, and are hence not transferable to other rooms. In this paper, we demonstrate the first algorithm that produces generic adversarial examples, which remain robust in an over-the-air attack that is not adapted to the specific environment. Hence, no prior knowledge of the room characteristics is required. Instead, we use room impulse responses (RIRs) to compute robust adversarial examples for arbitrary room characteristics and employ the ASR system Kaldi to demonstrate the attack. Further, our algorithm can utilize psychoacoustic methods to hide changes of the original audio signal below the human thresholds of hearing. In practical experiments, we show that the adversarial examples work for varying room setups, and that no direct line-of-sight between speaker and microphone is necessary. As a result, an attacker can create inconspicuous adversarial examples for any target transcription and apply these to arbitrary room setups without any prior knowledge.