Lightweight method detects electromagnetic attacks on image sensors
Lightweight Detection of Electromagnetic Signal Injection Attacks on Image Sensors
Cryptography and Security
Summary
Image sensors can be tricked by electromagnetic signals that change the pixels, causing AI systems to make wrong decisions. The authors propose a simple way to spot these attacks by checking special pixels on the sensor that are normally dark. Their method works well in tests, needs very little computing power, and doesn’t require changing the camera hardware. This can help keep vision systems safer from these sneaky attacks.
What this means in practice
- •For security engineers: Secure vision-based systems by detecting electromagnetic interference attacks using existing sensor features without hardware changes.
- •For automotive system developers: Protect automotive cameras from manipulation by monitoring optically black pixels to identify electromagnetic signal injection attacks in real time.
Authors
Youqian Zhang, Chunxi Yang, Eugene Yujun Fu, Sze Yiu Chau, Haibo Hu, Xiapu Luo
Abstract
Electromagnetic signal injection attacks (ESIA) pose a growing threat to image sensors, which are increasingly used in different intelligent systems. By emitting electromagnetic interference, adversaries can manipulate pixel values, potentially misleading downstream artificial intelligence (AI) models and causing unsafe decisions in these systems. We present a lightweight detection method that leverages optically black pixels, which are non-exposed pixels already present in many modern image sensors, to identify the attacks. Our detection approach achieves an area under the receiver operating characteristic curve (ROC-AUC) of up to 99.6\% and an Equal Error Rate (EER) as low as 0.027 across diverse attack conditions. Our method requires minimal computational overhead and no hardware modifications, making it a practical and effective defense for securing vision-based systems against ESIA.