Adversarial Robustness of Near-Field Millimeter-Wave Imaging under Waveform-Domain Attacks
Lhamo Dorje, Jordan Madden, Soamar Homsi, Xiaohua Li
TLDR
Millimeter-wave imaging systems are highly vulnerable to waveform-domain adversarial attacks, though deep learning methods show surprising robustness.
Key contributions
- Systematically studies adversarial robustness of mmWave imaging under waveform attacks.
- Proposes a white-box adversarial model and a differentiable imaging attack framework.
- Reveals mmWave imaging is highly vulnerable, allowing target concealment or alteration.
- Deep learning algorithms surprisingly exhibit higher robustness than classical methods.
Why it matters
This paper exposes critical security vulnerabilities in near-field mmWave imaging, used in safety-critical applications like airport screening. It highlights the urgent need to develop robust and secure imaging systems against waveform-domain attacks. The surprising resilience of deep learning methods also opens new avenues for defense.
Original Abstract
Near-field millimeter-wave (mmWave) imaging is widely deployed in safety-critical applications such as airport passenger screening, yet its own security remains largely unexplored. This paper presents a systematic study of the adversarial robustness of mmWave imaging algorithms under waveform-domain physical attacks that directly manipulate the image reconstruction process. We propose a practical white-box adversarial model and develop a differential imaging attack framework that leverages the differentiable imaging pipeline to optimize attack waveforms. We also construct a real measured dataset of clean and attack waveforms using a mmWave imaging testbed. Experiments on 10 representative imaging algorithms show that mmWave imaging is highly vulnerable to such attacks, enabling an adversary to conceal or alter targets with moderate transmission power. Surprisingly, deep-learning-based imaging algorithms demonstrate higher robustness than classical algorithms. These findings expose critical security risks and motivate the development of robust and secure mmWave imaging systems.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.