Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper investigates the adversarial robustness of near-field millimeter-wave (mmWave) imaging algorithms against waveform-domain attacks, where adversaries manipulate the image reconstruction process by injecting optimized waveforms. They propose a white-box attack framework leveraging a differentiable imaging pipeline and validate it on a real measured dataset. Results demonstrate high vulnerability across 10 imaging algorithms, with deep learning-based methods surprisingly showing greater robustness.
Millimeter-wave imaging, used in airport security, is surprisingly easy to fool with waveform-domain attacks, letting adversaries hide or alter objects with moderate power.
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.