{"ID":2896144,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.07773","arxiv_id":"2507.07773","title":"Rainbow Artifacts from Electromagnetic Signal Injection Attacks on 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.","short_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...","url_abs":"https://arxiv.org/abs/2507.07773","url_pdf":"https://arxiv.org/pdf/2507.07773v1","authors":"[\"Youqian Zhang\",\"Xinyu Ji\",\"Zhihao Wang\",\"Qinhong Jiang\"]","published":"2025-07-10T13:55:35Z","proceeding":"cs.CR","tasks":"[\"cs.CR\",\"cs.CV\"]","methods":"[]","has_code":false}