English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Deep neural networks (DNNs) have shown superior performance comparing totraditional image denoising algorithms. However, DNNs are inevitably vulnerablewhile facing adversarial attacks. In this paper, we propose an adversarialattack method named denoising-PGD which can successfully attack all the currentdeep denoising models while keep the noise distribution almost unchanged. Wesurprisingly find that the current mainstream non-blind denoising models(DnCNN, FFDNet, ECNDNet, BRDNet), blind denoising models (DnCNN-B, Noise2Noise,RDDCNN-B, FAN), plug-and-play (DPIR, CurvPnP) and unfolding denoising models(DeamNet) almost share the same adversarial sample set on both grayscale andcolor images, respectively. Shared adversarial sample set indicates that allthese models are similar in term of local behaviors at the neighborhood of allthe test samples. Thus, we further propose an indicator to measure the localsimilarity of models, called robustness similitude. Non-blind denoising modelsare found to have high robustness similitude across each other, whilehybrid-driven models are also found to have high robustness similitude withpure data-driven non-blind denoising models. According to our robustnessassessment, data-driven non-blind denoising models are the most robust. We useadversarial training to complement the vulnerability to adversarial attacks.Moreover, the model-driven image denoising BM3D shows resistance on adversarialattacks.

Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attack