Rainbow Artifacts from Electromagnetic Signal Injection Attacks on Image Sensors

TL;DR

This paper uncovers a new electromagnetic attack on CMOS image sensors that causes rainbow artifacts, leading to mispredictions in object detection systems and exposing a critical vulnerability in visual perception hardware.

Contribution

It introduces a novel electromagnetic injection attack causing rainbow artifacts in images, revealing an underexplored physical-layer vulnerability in image sensors.

Findings

Rainbow artifacts can be induced by electromagnetic interference.

Injected artifacts cause significant mispredictions in object detection.

The attack exploits the analog domain of CMOS image sensors.

Abstract

Image sensors are integral to a wide range of safety- and security-critical systems, including surveillance infrastructure, autonomous vehicles, and industrial automation. These systems rely on the integrity of visual data to make decisions. In this work, we investigate a novel class of electromagnetic signal injection attacks that target the analog domain of image sensors, allowing adversaries to manipulate raw visual inputs without triggering conventional digital integrity checks. We uncover a previously undocumented attack phenomenon on CMOS image sensors: rainbow-like color artifacts induced in images captured by image sensors through carefully tuned electromagnetic interference. We further evaluate the impact of these attacks on state-of-the-art object detection models, showing that the injected artifacts propagate through the image signal processing pipeline and lead to significant mispredictions. Our findings highlight a critical and underexplored vulnerability in the visual perception stack, highlighting the need for more robust defenses against physical-layer attacks in such systems.