# Adversarial Music: Real World Audio Adversary Against Wake-word Detection System

arXiv: https://arxiv.org/abs/1911.00126 · HTML: https://mlsanity.com/paper/1911.00126/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2019.

## Built on by (most cited first, 20 of 20)

- [Defending against Adversarial Audio via Diffusion Model](https://mlsanity.com/paper/2303.01507/) (2023)
- [Sequential Randomized Smoothing for Adversarially Robust Speech Recognition](https://mlsanity.com/paper/2112.03000/) (2021)
- [Adversarial Examples in the Physical World: A Survey](https://mlsanity.com/paper/2311.01473/) (2023)
- [Real-Time Neural Voice Camouflage](https://mlsanity.com/paper/2112.07076/) (2021)
- [Relational DNN Verification With Cross Executional Bound Refinement](https://mlsanity.com/paper/2405.10143/) (2024)
- [SoK: A Modularized Approach to Study the Security of Automatic Speech Recognition Systems](https://mlsanity.com/paper/2103.10651/) (2021)
- [Adversarial Attacks against Binary Similarity Systems](https://mlsanity.com/paper/2303.11143/) (2023)
- [Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection](https://mlsanity.com/paper/2604.14604/) (2026)
- [Adversarial Attack Attribution: Discovering Attributable Signals in Adversarial ML Attacks](https://mlsanity.com/paper/2101.02899/) (2021)
- [Robust Universal Adversarial Perturbations](https://mlsanity.com/paper/2206.10858/) (2022)
- [Watch What You Pretrain For: Targeted, Transferable Adversarial Examples on Self-Supervised Speech Recognition models](https://mlsanity.com/paper/2209.13523/) (2022)
- [Clean Label Attacks against SLU Systems](https://mlsanity.com/paper/2409.08985/) (2024)
- [On the Lack of Robustness of Binary Function Similarity Systems](https://mlsanity.com/paper/2412.04163/) (2024)
- [Emerging AI Security Threats for Autonomous Cars -- Case Studies](https://mlsanity.com/paper/2109.04865/) (2021)
- [Cross-Input Certified Training for Universal Perturbations](https://mlsanity.com/paper/2405.09176/) (2024)
- [Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models](https://mlsanity.com/paper/2506.11521/) (2025)
- [Cortical Features for Defense Against Adversarial Audio Attacks](https://mlsanity.com/paper/2102.00313/) (2021)
- [Audio Attacks and Defenses against AED Systems -- A Practical Study](https://mlsanity.com/paper/2106.07428/) (2021)
- [Employing chunk size adaptation to overcome concept drift](https://mlsanity.com/paper/2110.12881/) (2021)
- [Rigid Body Adversarial Attacks](https://mlsanity.com/paper/2502.05669/) (2025)

## Abstract (arXiv)

Voice Assistants (VAs) such as Amazon Alexa or Google Assistant rely on wake-word detection to respond to people's commands, which could potentially be vulnerable to audio adversarial examples. In this work, we target our attack on the wake-word detection system, jamming the model with some inconspicuous background music to deactivate the VAs while our audio adversary is present. We implemented an emulated wake-word detection system of Amazon Alexa based on recent publications. We validated our models against the real Alexa in terms of wake-word detection accuracy. Then we computed our audio adversaries with consideration of expectation over transform and we implemented our audio adversary with a differentiable synthesizer. Next, we verified our audio adversaries digitally on hundreds of samples of utterances collected from the real world. Our experiments show that we can effectively reduce the recognition F1 score of our emulated model from 93.4% to 11.0%. Finally, we tested our audio adversary over the air, and verified it works effectively against Alexa, reducing its F1 score from 92.5% to 11.0%.; We also verified that non-adversarial music does not disable Alexa as effectively as our music at the same sound level. To the best of our knowledge, this is the first real-world adversarial attack against a commercial-grade VA wake-word detection system. Our code and demo videos can be accessed at urlhttps://www.junchengbillyli.com/AdversarialMusic