Persons living with HIV (PLWH) continuously experience symptom burdens. Their symptom prevalence and severity are also quite different. Mobile health (mHealth) applications (apps) offer exceptional opportunities for using personalized interventions when and where PLWH are needed. This study aimed to demonstrate the development process of the symptom management (SM) app and the structure and content of it. Our research team systematically searched for evidence-based resources and summarized up-to-date evidence for symptom management and health education. Our multidisciplinary research team that included physicians, nurses, software engineers, and nursing professors, evaluated the structure and content of the drafted app. Both quantitative data and qualitative results were collected at a group discussion meeting. Quantitative data were scores of sufficient evidence, situational suitability, practicability, cost-effectiveness, and understandability (ranged from one to four) for 119 items of the app contents, including the health tracking module, the self-assessment module, coping strategies for 18 symptoms (80 items), medication management, complementary therapy, diet management, exercise, relaxation techniques, and the obtaining support module. The SM app was comprised of eight modules and provided several personalized symptom management functions, including assessing symptoms and receiving different symptom management strategies, tracking health indicators, and communicating with medical staff. The SM app was a promising and flexible tool for HIV symptom management. It provided PLWH with personalized symptom management strategies and facilitated the case management for medical staff. Future studies are needed to further test the app’s usability among PLWH users and its effects on symptom management.

State‐of‐the‐art adversarial attacks in the text domain have shown their power to induce machine learning models to produce abnormal outputs. The samples generated in these attacks have three important attributes: attack ability, transferability, and imperceptibility. However, compared with the other two attributes, the imperceptibility of adversarial examples has not been well investigated. Unlike the pixel‐level perturbations in images, adversarial perturbations in the text are usually traceable, reflecting changes in characters, words, or sentences. The generation of imperceptible samples in texts is more difficult than in images. Therefore, how to constrain adversarial perturbations added in the text is a crucial step to construct more natural adversarial texts. Unfortunately, recent studies merely select measurements to constrain the added adversarial perturbations, but none of them explain where these measurements are suitable, which one is better, and how they perform in different kinds of adversarial attacks. In this paper, we fill this gap by comparing the performance of these metrics in various attacks. Furthermore, we propose a stricter constraint for word‐level attacks to obtain more imperceptible samples. It is also helpful to enhance existing word‐level attacks for adversarial training.

This paper gives an impact analysis of Internet behavior's activity on the network survivability. The power-law exists in the distribution of network behavior's activity according to our empirical study. Besides, it is obvious that there is community effect in network communications. Our results overthrow some usual hypothesises as preconditions of trustworthy network study. It's helpful to assess network vulnerability and to enhance network survivability.

No abstract