Fast C&amp;W: A Fast Adversarial Attack Algorithm to Fool SAR Target Recognition With Deep Convolutional Neural Networks

Du, Chuan; Huo, Chaoying; Zhang, Lei; Chen, Bin; Yuan, Yijun

doi:10.1109/lgrs.2021.3058011

Cited by 30 publications

(15 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Li et al [25] generated abundant adversarial examples for CNN-based SAR image classifiers through the basic FGSM method and systematically evaluated critical factors affecting the attack performance. Du et al [26] designed a Fast C&W algorithm to improve the efficiency of generating adversarial examples by introducing an encoderdecoder model. To enhance the universality and feasibility of adversarial perturbations, the work in [27] presented a universal local adversarial network to generate universal adversarial perturbations for the target region of SAR images.…”

Section: Of 21mentioning

confidence: 99%

TAN: A Transferable Adversarial Network for DNN-based UAV SAR Automatic Target Recognition Models

Du¹,

Sun²,

Sun³

et al. 2023

Preprint

View full text Add to dashboard Cite

In recent years, the unmanned aerial vehicle (UAV) synthetic aperture radar (SAR) has become a highly sought-after topic for its wide applications in the field of target recognition, detection, and tracking. However, SAR automatic target recognition (ATR) models based on deep neural networks (DNN) are suffering from adversarial examples. Generally, non-cooperators rarely disclose any information about SAR-ATR models, making adversarial attacks challenging. In this situation, we propose Transferable Adversarial Network (TAN) to attack these models with highly transferable adversarial examples. The proposed method improves the transferability via a two-player game, in which we simultaneously train two encoder-decoder models: a generator that crafts malicious samples through a one-step forward mapping from original data, and an attenuator that weakens the effectiveness of malicious samples by capturing the most harmful deformations. In particular, compared to traditional iterative methods, our approach is able to one-step map original samples to adversarial examples, thus enabling real-time attacks. Experimental results indicate that the proposed approach achieves state-of-the-art transferability with acceptable adversarial perturbations and minimum time costs compared to existing attack methods, i.e., it excellently realizes real-time transferable adversarial attacks.

show abstract

Section: Of 21mentioning

confidence: 99%

TAN: A Transferable Adversarial Network for DNN-based UAV SAR Automatic Target Recognition Models

Du¹,

Sun²,

Sun³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In terms of data-dependent perturbations, Li et al [26] use the FGSM and BIM algorithms to produce abundant adversarial examples for the CNN-based SAR image classification model and comprehensively analyze various factors affecting the attack success rate. The work in [27] presents a Fast C&W algorithm for realtime attacks that introduces an encoder network to generate adversarial examples through one-step forward mapping of SAR images. To enhance the universality of adversarial perturbations, Wang et al [28] utilize the method proposed in [19] to craft UAPs for SAR images and achieve high attack success rates.…”

Section: Introductionmentioning

confidence: 99%

ULAN: A Universal Local Adversarial Network for SAR Target Recognition Based on Layer-wise Relevance Propagation

Du¹,

Bi²,

Du³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recent studies have proven that synthetic aperture radar (SAR) automatic target recognition (ATR) models based on deep neural networks (DNN) are vulnerable to adversarial examples. However, existing attacks are easily failed in the case where adversarial perturbations cannot be fully fed to victim models. We call this situation perturbation offset. Moreover, since background clutter takes up most of the areas in SAR images and has low relevance to recognition results, fooling models with global perturbations is quite inefficient. This paper proposes a semi-whitebox attack network, called Universal Local Adversarial Network (ULAN), to generate universal adversarial perturbations (UAP) for the target regions of SAR images. In the proposed network, we calculate the model’s attention heatmaps through layer-wise relevance propagation (LRP), which is used to locate the target regions of SAR images that have high relevance to recognition results. In particular, we utilize a generator based on the U-Net to learn the mapping from noise to UAPs and craft adversarial examples by adding the generated local perturbations to target regions. Experiments indicate that the proposed method fundamentally prevents perturbation offset and achieves comparable attack performance to conventional global UAPs by perturbing only a quarter or less of SAR image areas.

show abstract

“…Szegedy et al [13] first discover that by injecting well-designed tiny perturbations into image samples, adversarial examples can be intentionally produced to cause the recognition model to misclassify. This process of generating adversarial examples is named as "adversarial attack", which has become a recent study trend [14][15][16][17][18][19] in the research field of remote sensing, radar, radio, etc. In radar signal processing, [14,15] verify that high-resolution range profile (HRRP) and SAR image target recognition models can be attacked successfully by well-designed adversarial examples.…”

Section: Introductionmentioning

confidence: 99%

“…In radar signal processing, [14,15] verify that high-resolution range profile (HRRP) and SAR image target recognition models can be attacked successfully by well-designed adversarial examples. A faster C&W adversarial attack algorithm [16] is proposed to effectively fool deep CNN-based SAR target classifiers and meet real-time requirements. In the field of remote sensing, Li et al [17] provide abundant experiments and insightful analysis on the adversarial attack of the deep CNNsbased remote sensing image scene classification.…”

Section: Introductionmentioning

confidence: 99%

Adversarial Attack for SAR Target Recognition Based on UNet-Generative Adversarial Network

Zhang

2021

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Some recent articles have revealed that synthetic aperture radar automatic target recognition (SAR-ATR) models based on deep learning are vulnerable to the attacks of adversarial examples and cause security problems. The adversarial attack can make a deep convolutional neural network (CNN)-based SAR-ATR system output the intended wrong label predictions by adding small adversarial perturbations to the SAR images. The existing optimization-based adversarial attack methods generate adversarial examples by minimizing the mean-squared reconstruction error, causing smooth target edge and blurry weak scattering centers in SAR images. In this paper, we build a UNet-generative adversarial network (GAN) to refine the generation of the SAR-ATR models’ adversarial examples. The UNet learns the separable features of the targets and generates the adversarial examples of SAR images. The GAN makes the generated adversarial examples approximate to real SAR images (with sharp target edge and explicit weak scattering centers) and improves the generation efficiency. We carry out abundant experiments using the proposed adversarial attack algorithm to fool the SAR-ATR models based on several advanced CNNs, which are trained on the measured SAR images of the ground vehicle targets. The quantitative and qualitative results demonstrate the high-quality adversarial example generation and excellent attack effectiveness and efficiency improvement.

show abstract

Fast C&W: A Fast Adversarial Attack Algorithm to Fool SAR Target Recognition With Deep Convolutional Neural Networks

Cited by 30 publications

References 14 publications

TAN: A Transferable Adversarial Network for DNN-based UAV SAR Automatic Target Recognition Models

TAN: A Transferable Adversarial Network for DNN-based UAV SAR Automatic Target Recognition Models

ULAN: A Universal Local Adversarial Network for SAR Target Recognition Based on Layer-wise Relevance Propagation

Adversarial Attack for SAR Target Recognition Based on UNet-Generative Adversarial Network

Contact Info

Product

Resources

About