Spatio-temporal attack improves deception of cognitive radars under real conditions
Bridging Digital Deception and Physical Fidelity: A Spatio-Temporal Attack on Cognitive Radars
Machine LearningCryptography and Security
Summary
Cognitive radars use advanced deep learning to process signals, but they can be tricked by carefully designed attacks. Existing attacks don’t work well across different radar systems or when signal conditions change in real life. The authors propose a new attack method called Segmented Spatio-Temporal Attack that breaks down signals into segments and accounts for physical effects like noise and distortion. This method fools a wider variety of radar systems and still works after passing through real-world signal noise. It helps test the security of radar systems against digital and physical threats.
What this means in practice
- •For radar system developers: Test and strengthen radar signal processing against attacks that survive real-world distortions across different model types.
- •For electronic warfare teams: Assess and improve cognitive electronic warfare techniques by simulating attacks that bridge digital deception and physical signal realism.
Authors
Tongrun Xing, Yongjun Dai, Xuan Liao, Zhiwen Zhang, Tong Zhou, Longlong Zhang, Tian Jiang
Abstract
As cognitive radars evolve towards the end-to-end processing of one-dimensional complex baseband sequences, deep networks face severe adversarial threats. However, existing attacks encounter dual limitations in practical electronic warfare: low cross-architecture transferability and severe vulnerability to physical channel distortions, which degrades their tactical reliability. To overcome these bottlenecks, we propose a physical prior-driven Segmented Spatio-Temporal Attack (SSTA). First, a global-local feature decoupling segmentation mechanism interrupts the adversarial gradients' dependence on long-range sequence coherence, bridging the cross-architecture feature gap. Second, moving beyond static norm constraints devoid of physical semantics, we abstract channel distortions into differentiable spatio-temporal operators, integrating them into momentum iterations via an Expectation over Transformation (EoT) strategy. Comprehensive cross-evaluations across 9 heterogeneous models spanning CNNs, RNNs, and Transformers demonstrate that SSTA outperforms the state-of-the-art baseline by 10.36% in Average Black-Box Attack Success Rate. Furthermore, baseband equivalent simulations confirm that the generated waveforms survive extreme physical distortions and, after matched filtering, achieve zero main-lobe attenuation (0 dB) with noise floor lift strictly within Constant False Alarm Rate tolerances. SSTA successfully unifies digital-domain deception and physical-domain fidelity, providing crucial support for CEW security assessment.