Giving AI a headache: acoustic adversarial attacks to computer vision applications

Abstract

Artificial Intelligence (AI) is increasingly used to automate a variety of real-world computer vision (CV) applications, such as autonomous vehicle control, facial recognition, and security cameras. Recent research has shown that acoustic vibration can induce real physical motion in cameras, interfering with their internal stabilization mechanisms. Because the motion falls outside the conditions the stabilization system was designed to handle, the system introduces artifacts into the frame, causing AI-based CV models to misclassify, miss targets, or hallucinate objects. Previous work used ultrasonic frequencies (>20 kHz) to perform short-range attacks, which limits them to short distances due to the attenuation exhibited by high frequencies. In this work, we investigate acoustic attacks using lower frequencies in the audible range (<20 kHz), and we further expand our analysis to include how various image and object features are affected by the attacks. Specifically, we performed physical experiments to demonstrate the viability of our attacks on an off-theshelf object detection model (YOLO11) by resonating a commercially available camera with various frequencies. Based on our results, we provide insights into several factors that make an AI CV system more vulnerable to these attacks, which could help inform the development of future mitigation strategies.

@inproceedings{10.1117/12.3093699,
author = {Nicole Villavicencio-Gardu{\~n}o and Maksim Ekin Eren and Milo Prisbrey and Ben Migliori and Michael Teti},
title = {{Giving AI a headache: acoustic adversarial attacks to computer vision applications}},
volume = {14046},
booktitle = {Assurance and Security for AI-enabled Systems 2026},
editor = {Joshua D. Harguess and Nathaniel D. Bastian and Chris M. Ward},
organization = {International Society for Optics and Photonics},
publisher = {SPIE},
pages = {1404609},
keywords = {adversarial AI, adversarial machine learning, computer vision, adversarial attacks, adversarial acoustics , hardware, artificial intelligence (AI)},
year = {2026},
doi = {10.1117/12.3093699},
URL = {https://doi.org/10.1117/12.3093699}
}

Maksim E. Eren

Scientist

Maksim E. Eren is a Scientist at Los Alamos National Laboratory, specializing in machine learning and artificial intelligence for large-scale data science applications.