With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks (DNNs) have been recently found vulnerable to well-designed input samples called adversarial examples. Adversarial perturbations are imperceptible to human but can easily fool DNNs in the testing/deploying stage. The vulnerability to adversarial examples becomes one of the major risks for applying DNNs in safety-critical environments. Therefore, attacks and defenses on adversarial examples draw great attention. In this paper, we review recent findings on adversarial examples for DNNs, summarize the methods for generating adversarial examples, and propose a taxonomy of these methods. Under the taxonomy, applications for adversarial examples are investigated. We further elaborate on countermeasures for adversarial examples. In addition, three major challenges in adversarial examples and the potential solutions are discussed.

Distributed Denial of Service (DDoS) attacks grow rapidly and become one of the fatal threats to the Internet. Automatically detecting DDoS attack packets is one of the main defense mechanisms. Conventional solutions monitor network traffic and identify attack activities from legitimate network traffic based on statistical divergence. Machine learning is another method to improve identifying performance based on statistical features. However, conventional machine learning techniques are limited by the shallow representation models. In this paper, we propose a deep learning based DDoS attack detection approach (DeepDefense). Deep learning approach can automatically extract high-level features from low-level ones and gain powerful representation and inference. We design a recurrent deep neural network to learn patterns from sequences of network traffic and trace network attack activities. The experimental results demonstrate a better performance of our model compared with conventional machine learning models. We reduce the error rate from 7.517% to 2.103% compared with conventional machine learning method in the larger data set.

Emerging clustered regularly interspaced short palindromic repeat/associated protein (CRISPR/Cas) genome editing technology shows great potential in gene therapy. However, proteins and nucleic acids suffer from enzymatic degradation in the physiological environment and low permeability into cells. Exploiting carriers to protect the CRISPR system from degradation, enhance its targeting of specific tissues and cells, and reduce its immunogenicity is essential to stimulate its clinical applications. Here, the authors review the state‐of‐the‐art CRISPR delivery systems and their applications, and describe strategies to improve the safety and efficacy of CRISPR mediated genome editing, categorized by three types of cargo formats, that is, Cas: single‐guide RNA ribonucleoprotein, Cas mRNA and single‐guide RNA, and Cas plasmid expressing CRISPR/Cas systems. The authors hope this review will help develop safe and efficient nanomaterial‐based carriers for CRISPR tools.

This study was to explore the mechanism by which reactive oxygen species (ROS)-induced oxidative stress involved in the pathogenesis of fungal keratitis using an in vivo experimental keratitis mouse model and an in vitro culture model of human corneal epithelial cells (HCECs). Compared to normal control mice and HCECs, ROS production was markedly increased in fungal corneas and HCECs exposed to Candida albicans, accompanied by p38 mitogen-activated protein kinases (MAPK) activation. Increased products of oxidative markers, malondialdehyde (MDA), 4–hydroxynonenal (HNE), mitochondria DNA 8-OHdG and aconitase-2 were observed in fungal infected corneas and HCECs. Fungal infection also increased the mRNA expression and protein production of heme oxygenase-1 (HMOX1) and cyclooxygenase-2 (COX2), with suppressed levels of antioxidant enzymes, superoxide dismutase-1 (SOD1), glutathione peroxidase-1 (GPx1) and peroxiredoxin-4 (PRDX4). Interestingly, the levels of ROS, oxidative markers and oxygenases were significantly reduced by co-cultured p38 inhibitor SB203580. Furthermore, SB203580 restored the levels of antioxidant enzymes suppressed by fungus. Our findings demonstrated for the first time that ROS-induced oxidative injury is involved in pathogenesis of fungal keratitis via p38 MAPK pathway, suggesting the novel therapeutic targets for the potential treatment of fungal keratitis.