English

A Human-in-the-Middle Attack against Object Detection Systems

Robotics 2024-07-12 v4 Computer Vision and Pattern Recognition

Abstract

Object detection systems using deep learning models have become increasingly popular in robotics thanks to the rising power of CPUs and GPUs in embedded systems. However, these models are susceptible to adversarial attacks. While some attacks are limited by strict assumptions on access to the detection system, we propose a novel hardware attack inspired by Man-in-the-Middle attacks in cryptography. This attack generates a Universal Adversarial Perturbations (UAP) and injects the perturbation between the USB camera and the detection system via a hardware attack. Besides, prior research is misled by an evaluation metric that measures the model accuracy rather than the attack performance. In combination with our proposed evaluation metrics, we significantly increased the strength of adversarial perturbations. These findings raise serious concerns for applications of deep learning models in safety-critical systems, such as autonomous driving.

Keywords

Cite

@article{arxiv.2208.07174,
  title  = {A Human-in-the-Middle Attack against Object Detection Systems},
  author = {Han Wu and Sareh Rowlands and Johan Wahlstrom},
  journal= {arXiv preprint arXiv:2208.07174},
  year   = {2024}
}

Comments

Accepted by IEEE Transactions on Artificial Intelligence, 2024

R2 v1 2026-06-25T01:42:48.215Z