The study of effective methods for removing image speckle remains a significant challenge in image processing. In contrast to additive noise, speckle noise is a multiplicative noise whose intensity is proportional to the signal. This results in a noise distribution that exhibits a high dependence on the signal intensity throughout the image, rendering it difficult to remove. Therefore, we present a novel approach to speckle noise removal using dynamical threshold-based fractional anisotropic diffusion (named as DTFAD) in this study. The method simultaneously considers both gradient and gray scale information in the image. In addition, the fractional derivative is integrated with anisotropic diffusion in the DTFAD model, which enhances the image denoising effect to preserve the fundamental features and edges of the image. The design of a dynamic threshold function in the diffusion coefficient enables the diffusion pattern and intensity to adaptively change according to image information, thus effectively removing speckle noise. We establish the well-posedness of the DTFAD model and implement it using an explicit finite difference scheme. Extensive experiments demonstrate that the DTFAD model outperforms traditional anisotropic diffusion techniques, and achieves a superior balance between denoising performance and texture preservation. This evidence demonstrates that the DTFAD model has the potential to be applied in practical engineering.

Deep neural networks (DNNs) and natural language processing (NLP) systems have developed rapidly and have been widely used in various real-world fields. However, they have been shown to be vulnerable to backdoor attacks. Specifically, the adversary injects a backdoor into the model during the training phase, so that input samples with backdoor triggers are classified as the target class. Some attacks have achieved high attack success rates on the pre-trained language models (LMs), but there have yet to be effective defense methods. In this work, we propose a defense method based on deep model mutation testing. Our main justification is that backdoor samples are much more robust than clean samples if we impose random mutations on the LMs and that backdoors are generalizable. We first confirm the effectiveness of model mutation testing in detecting backdoor samples and select the most appropriate number of mutants and mutation operators. We then systematically defend against three extensively studied backdoor attack levels (i.e., char-level, word-level, and sentence-level) by detecting backdoor samples. We also make the first attempt to defend against the latest style-level backdoor attacks. We evaluate our approach on three benchmark datasets (i.e., IMDB, Yelp, and AG news) and three style transfer datasets (i.e., SST-2, Hate-speech, and AG news). The extensive experimental results demonstrate that our approach can detect backdoor samples more efficiently and accurately than the three state-of-the-art defense approaches.

The black-box nature of the Deep Neural Network (DNN) makes it difficult for people to understand why it makes a specific decision, which restricts its applications in critical tasks. Recently, many interpreters (interpretation methods) are proposed to improve the transparency of DNNs by providing relevant features in the form of a saliency map. However, different interpreters might provide different interpretation results for the same classification case, which motivates us to conduct the robustness evaluation of interpreters.