1 code implementation • 30 Jan 2024 • Bowen Peng, Bo Peng, Jingyuan Xia, Tianpeng Liu, Yongxiang Liu, Li Liu
Recently, there has been increasing concern about the vulnerability of deep neural network (DNN)-based synthetic aperture radar (SAR) automatic target recognition (ATR) to adversarial attacks, where a DNN could be easily deceived by clean input with imperceptible but aggressive perturbations.
no code implementations • 21 Dec 2023 • Peng Zhao, Jiehua Zhang, Bowen Peng, Longguang Wang, YingMei Wei, Yu Liu, Li Liu
2) BNNs consistently exhibit better adversarial robustness under black-box attacks.
4 code implementations • 31 Aug 2023 • Bowen Peng, Jeffrey Quesnelle, Honglu Fan, Enrico Shippole
Rotary Position Embeddings (RoPE) have been shown to effectively encode positional information in transformer-based language models.
no code implementations • 4 Apr 2023 • Bowen Peng, Jianyue Xie, Bo Peng, Li Liu
The proposed method contributes a mixed clutter variants generation strategy and a new inference branch equipped with channel-weighted mean square error (CWMSE) loss for invariant representation learning.
1 code implementation • 11 Sep 2022 • Bowen Peng, Bo Peng, Jie zhou, Jianyue Xie, Li Liu
Toward building more robust DNN-based SAR ATR models, this article explores the domain knowledge of SAR imaging process and proposes a novel Scattering Model Guided Adversarial Attack (SMGAA) algorithm which can generate adversarial perturbations in the form of electromagnetic scattering response (called adversarial scatterers).