App Security Research Articles

Centralized Vulnerability Management and SDK Risk Assessment Framework for Enhanced App security

Centralized Vulnerability Management and SDK Risk Assessment Framework for Enhanced App security

An empirical study of AI techniques in mobile applications

The integration of artificial intelligence (AI) into mobile applications has significantly transformed various domains, enhancing user experiences and providing personalized services through advanced machine learning (ML) and deep learning (DL) technologies. AI-driven mobile apps typically refer to applications that leverage ML/DL technologies to perform key tasks such as image recognition and natural language processing. Despite existing research exploring how mobile apps exploit AI techniques, they have the following main limitations: (1) Most existing studies focus on DL-based apps, with limited research on ML-based apps. (2) Existing research typically focuses on investigating the apps and the technologies utilized in the apps, lacking user-level analysis. (3) The number of apps studied is limited, with only 1,000 to 2,000 ML/DL apps identified after filtering. To fill the gap, in this paper, we conducted the most extensive empirical study on AI applications, exploring on-device ML apps, on-device DL apps, and AI service-supported (cloud-based) apps. Our study encompasses 56,682 real-world AI applications, focusing on three crucial perspectives: (1) Application analysis, where we analyze the popularity of AI apps and investigate the update states of AI apps; (2) Framework and model analysis, where we analyze AI framework usage and AI model protection; (3) User analysis, where we examine user privacy protection and user review attitudes. Our study has strong implications for AI app developers, users, and AI R&D. On one hand, our findings highlight the growing trend of AI integration in mobile applications, demonstrating the widespread adoption of various AI frameworks and models. On the other hand, our findings emphasize the need for robust model protection to enhance app security. Additionally, our study highlights the importance of user privacy and presents user attitudes towards the AI technologies utilized in current AI apps. We provide our AI app dataset (currently the most extensive AI app dataset) as an open-source resource for future research on AI technologies utilized in mobile applications.

Botnet Attack Identification and Mitigation condition Software-Defined Networks Utilizing CNN Algorithm

One new design that makes managing and communicating across large-scale networks easier and more flexible is software-defined networking, or SDN. It allows for the smooth and dynamic execution of complicated network choices via programmable and centralized interfaces. But SDN opens doors for people and companies to tailor network apps to their needs, allowing them to enhance services. On the other hand, it began to encounter a host of new privacy and security issues and brought the dangers of one point of failure all at once. In most cases, hackers use OpenFlow switches to conduct botnets or distributed Denial of Service (DDoS) assaults against the controller. Popular security apps that use deep learning (DL) to quickly identify and counteract attacks are on the rise. Here, we examine botnet-based DDoS attack detection using DL approaches in an SDN-supported context and demonstrate their performance. For the assessment, we utilize a dataset that we just created ourselves. In order to choose the most useful subset of characteristics, we used weighting of features and tuning techniques. Using both a synthetic dataset and actual testbed conditions, we validate the measurements or simulation results. The primary objective of this research is to identify botnet-based DDoS assaults using easily-obtained characteristics and data using a lightweight DL approach with baseline hyper-parameters. We found that the DL technique's performance is affected by the optimal subset of features, and that the accuracy of predictions of the same approach may be varied with a different collection of features. Lastly, our empirical findings show that the CNN approach works better than both the dataset and the actual testbed environments. With CNN, the detection rate for typical flows is 99% and for malicious flows it drops to 97%.

Feeding trust: exploring key drivers, moderators and consequences related to food app usage

PurposeThis paper aims to utilize an extended involvement-commitment and trust commitment model to examine post-consumption decisions related to food delivery app use.Design/methodology/approachA self-administered online survey was used to collect data from food delivery app users in the USA.FindingsFindings validate a favorable role of perceived app security and menu description on trust in app recommendations. Trust was found to be positively related to involvement, commitment and willingness to provide feedback. The positive moderating role of perceived convenience and rewards and incentives was also confirmed in relation to consumers’ trust in app recommendations, and involvement and commitmentOriginality/valueA key contribution of this study includes the development of a comprehensive model to understand postconsumption decisions related to the usage of food delivery apps. To the best of the authors’ knowledge, this study is also the first to unveil the antecedent and moderating factors related to food delivery app users’ willingness to provide feedback, share personal data and to pay more.

A Keypad-Based Mobile App Security Alert System with Virtual Private Network and Short Message Service Integration

In the digital age, mobile devices are integral to daily life, making robust security measures essential for protecting sensitive data. This paper presents the development of a mobile application aimed at enhancing personal security through a keypad-based authentication system, integrated with Short Message Service (SMS) and Virtual Private Network (VPN) functionalities. The intuitive interface of keypads allows users to swiftly send predefined emergency messages with a single keystroke, including their current location and urgency details. The application ensures encrypted and secure communication via a VPN and leverages SMS for reliable real-time notifications, even in areas with limited connectivity. A user-centered design approach, utilizing React JS for frontend development and Bootstrap for a responsive UI, ensures accessibility and ease of use for individuals with varying levels of technological proficiency. Rigorous testing validates the application's functionality and performance, demonstrating its potential to streamline emergency communication and enhance personal security in critical situations.

Pengaruh Mobile App Attractiveness, Functionality, Security dan Consumer Fulfillment Terhadap E-Loyalty dengan E-Satisfaction Sebagai Intervening pada E-Commerce Tokopedia

With e-satisfaction serving as a mediator in the Tokopedia online business, the purpose of this study is to examine the impact of versatile application attractiveness, functionality, security, and customer fulfilment on e-loyalty. For the quantitative research approach, data were gathered through a survey. The members in this study are Tokopedia web based business clients who have made purchases there. The sample for this study is made up of some Tokopedia e-commerce customers who have purchased at least one mobile phone product since January 2023. Tokopedia is only available to customers in Greater Jakarta. In this study, probability sampling is used. The SEM-PLS approach is used by the specialist. The study found that attractiveness, security, and customer fulfillment of mobile apps had a significant impact on e-satisfaction. Functionality had no significant impact on e-satisfaction. E-loyalty is also significantly influenced by customer satisfaction and customer fulfillment. E-satisfaction had no significant impact on moderating customer fulfillment to e-loyalty in this study.

Applying Digital Technology to Understand Human Experiences of Climate Change Impacts on Food Security and Mental Health: Scoping Review.

The global impact of climate change ranges from intense heatwaves to extreme weather events that endanger entire ecosystems and people's way of life. Adverse climate change events place undue stress on food and health systems, with consequences for human food security and mental health status. Ubiquitous digital devices, such as smartphones, have the potential to manage existing and emerging climate-related crises, given their ability to enable rapid response, instant communication, and knowledge sharing. This scoping review aimed to identify digital apps being used to capture or address climate change impacts on food security and mental health to inform the development of a digital citizen science initiative. A scoping review was conducted using 3 peer-reviewed databases (PubMed, IEEE Xplore, and Web of Science) and manual gray literature searches of relevant organizational (ie, governmental and nonprofit) websites to identify articles and reports published between January 2012 and July 2023. Three separate searches were conducted in each database to identify digital apps focused on climate change and (1) food security, (2) mental health, and (3) food security and mental health. Two reviewers conducted initial screening, with a third reviewer resolving any discrepancies. Articles focused on climate change impacts on wildlife or agriculture (ie, not human food security) were excluded. Full-text screening was conducted for shortlisted articles, and a final data abstraction table was generated, summarizing key app features, contextual factors, and participant involvement. From the 656 records screened, 14 digital apps met the inclusion criteria. The food security apps (n=7, 50%) aimed to capture traditional knowledge to preserve food systems, conduct food security assessments, and aid users in decreasing food insecurity risk. The mental health apps (n=7, 50%) assessed climate change-related stress and provided users with coping strategies following adverse weather events. No digital apps examined the intersection of climate change, food security, and mental health. Key app features included user-to-user communication (n=5, 36%), knowledge databases (n=5, 36%), data collection and analysis (n=3, 21%), gamification (n=1, 7%), and educational resources (n=2, 14%) to address climate change impacts on food security or mental health. In total, 3 approaches to participant involvement were used across studies, including contributory (n=1, 7%), collaborative (n=1, 7%), and cocreative (n=1, 7%) approaches, to ensure the relevance and use of digital apps. Most digital apps identified provided a service to citizens to either prevent adverse climate change-related health impacts or manage these effects following an acute event or a natural disaster. The capacity of ubiquitous digital tools to enable near real-time communication, the involvement of various stakeholder groups, and their ability to share relevant educational resources in a timely manner are important for developing tailored climate change adaptation and mitigation strategies across jurisdictions.

Multi-factor Authentication Framework for Secured Data Access in Cloud Computing

Aims and Background: Accessing data services on the cloud raises serious concerns about security and privacy. To verify a client's stated identity, the existing authentication approach uses just one authentication factor. However, traditional techniques of one-factor authentication are inefficient since they demand an excessive amount of user information and expose their private data to eavesdropping. Methods: Cloud-based data storage is susceptible to both external and internal threats. Information security relies heavily on authentication, which is a method for verifying user identities before granting them access to protected data. When it comes to protecting data in a cloud computing environment from the most cutting-edge methods of attack, traditional password authentication simply isn't enough. For the purpose of protecting user identities in the cloud, this study presents interactive multi-layer authentication systems. Various access control policies are used when validating users in the cloud. Registration, permissions, and authentication factors for users are all parts of the cloud app's security process. Results: An intrusion detection system is built into the security mechanism to help identify people who could be malevolent. Various techniques are available for user identity verification, including intrusion detection, access control, and multi-factor authentication. The last step is to encrypt the data so that no one else can read it. Conclusion: To guarantee the effectiveness and accuracy of the suggested frameworks and methodology, they are experimentally evaluated. There were few false positives and a high detection rate.

Nudging Data Privacy of Mobile Health Applications in Saudi Arabia

Mobile health apps are a digital era revolution, facilitating direct patient-physician communication, lab and test orders, and medication refills. Despite these benefits, security and privacy issues arise due to handling sensitive data. This paper assesses the security and privacy of Saudi Arabian mobile healthcare apps, gauging compliance with the Personal Data Protection Law (PDPL). Results highlight varied PDPL compliance, underscoring the imperative for enhanced security measures in the digital healthcare landscape.

Patients and Stakeholders' Perspectives Regarding the Privacy, Security, and Confidentiality of Data Collected via Mobile Health Apps in Saudi Arabia: Protocol for a Mixed Method Study.

There is data paucity regarding users' awareness of privacy concerns and the resulting impact on the acceptance of mobile health (mHealth) apps, especially in the Saudi context. Such information is pertinent in addressing users' needs in the Kingdom of Saudi Arabia (KSA). This article presents a study protocol for a mixed method study to assess the perspectives of patients and stakeholders regarding the privacy, security, and confidentiality of data collected via mHealth apps in the KSA and the factors affecting the adoption of mHealth apps. A mixed method study design will be used. In the quantitative phase, patients and end users of mHealth apps will be randomly recruited from various provinces in Saudi Arabia with a high population of mHealth users. The research instrument will be developed based on the emerging themes and findings from the interview conducted among stakeholders, app developers, health care professionals, and users of mHealth apps (n=25). The survey will focus on (1) how to improve patients' awareness of data security, privacy, and confidentiality; (2) feedback on the current mHealth apps in terms of data security, privacy, and confidentiality; and (3) the features that might improve data security, privacy, and confidentiality of mHealth apps. Meanwhile, specific sections of the questionnaire will focus on patients' awareness, privacy concerns, confidentiality concerns, security concerns, perceived usefulness, perceived ease of use, and behavioral intention. Qualitative data will be analyzed thematically using NVivo version 12. Descriptive statistics, regression analysis, and structural equation modeling will be performed using SPSS and partial least squares structural equation modeling. The ethical approval for this research has been obtained from the Biomedical and Scientific Research Ethics Committee, University of Warwick, and the Medical Research and Ethics Committee Ministry of Health in the KSA. The qualitative phase is ongoing and 15 participants have been interviewed. The interviews for the remaining 10 participants will be completed by November 25, 2023. Preliminary thematic analysis is still ongoing. Meanwhile, the quantitative phase will commence by December 10, 2023, with 150 participants providing signed and informed consent to participate in the study. The mixed methods study will elucidate the antecedents of patients' awareness and concerns regarding the privacy, security, and confidentiality of data collected via mHealth apps in the KSA. Furthermore, pertinent findings on the perspectives of stakeholders and health care professionals toward the aforementioned issues will be gleaned. The results will assist policy makers in developing strategies to improve Saudi users'/patients' adoption of mHealth apps and addressing the concerns raised to benefit significantly from these advanced health care modalities. DERR1-10.2196/54933.

An optimized neural network with AdaHessian for cryptojacking attack prediction for Securing Crypto Exchange Operations of MEC applications

Bitcoin exchange security is crucial because of MEC's widespread use. Cryptojacking has compromised MEC app security and bitcoin exchange ecosystem functionality. This paper propose a cutting-edge neural network and AdaHessian optimization technique for cryptojacking prediction and defense. We provide a cutting-edge deep neural network (DNN) cryptojacking attack prediction approach employing pruning, post-training quantization, and AdaHessian optimization. To solve these problems, this paper apply pruning, post-training quantization, and AdaHessian optimization. A new framework for quick DNN training utilizing AdaHessian optimization can detect cryptojacking attempts with reduced computational cost. Pruning and post-training quantization improve the model for low-CPU on-edge devices. The proposed approach drastically decreases model parameters without affecting Cryptojacking attack prediction. The model has Recall 98.72%, Precision 98.91%, F1-Score 99.09%, MSE 0.0140, RMSE 0.0137, and MAE 0.0139. Our solution beats state-of-the-art approaches in precision, computational efficiency, and resource consumption, allowing more realistic, trustworthy, and cost-effective machine learning models. We address increasing cybersecurity issues holistically by completing the DNN optimization-security loop. Securing Crypto Exchange Operations delivers scalable and efficient Cryptojacking protection, improving machine learning, cybersecurity, and network management.

MRAAC: A Multi-Stage Risk-Aware Adaptive Authentication and Access Control Framework for Android

Adaptive authentication enables smartphones and enterprise apps to decide when and how to authenticate users based on contextual and behavioral factors. In practice, a system may employ multiple policies to adapt its authentication mechanisms and access controls to various scenarios. However, existing approaches suffer from contradictory or insecure adaptations, which may enable attackers to bypass the authentication system. Besides, most existing approaches are inflexible and do not provide desirable access controls. We design and build a multi-stage risk-aware adaptive authentication and access control framework (MRAAC), which provides the following novel contributions: Multi-stage: MRAAC organizes adaptation policies in multiple stages to handle different risk types and progressively adapts authentication mechanisms based on context, resource sensitivity, and user authenticity. Appropriate access control: MRAAC provides libraries to enable sensitive apps to manage the availability of their in-app resources based on MRAAC’s risk awareness. Extensible: While existing proposals are tailored to cater to a single use case, MRAAC supports a variety of use cases with custom risk models. We exemplify these advantages of MRAAC by deploying it for three use cases: an enhanced version of Android Smart Lock, guest-aware continuous authentication, and corporate app for BYOD. We conduct experiments to quantify the CPU, memory, latency, and battery performance of MRAAC. Our evaluation shows that MRAAC enables various stakeholders (device manufacturers, enterprise and secure app developers) to provide complex adaptive authentication workflows on COTS Android with low processing and battery overhead.

Assessing the Quality, Privacy, and Security of Breast Cancer Apps for Arabic Speakers: Systematic Search and Review of Smartphone Apps.

Breast cancer is a widespread disease, and its incidence is rapidly increasing in the Middle East and North Africa region. With the increasing availability of smartphone apps for various health purposes, breast cancer apps have emerged as tools for raising awareness, providing support, and empowering women affected by this disease. These apps offer many features, including information on breast cancer risk factors, self-examination guides, appointment reminders, and community support groups or hotlines. Using apps raises the risk of privacy and security issues, and we hope that examining these features of the apps will contribute to the understanding of how technology can be used to improve these apps and provide insights for future development and improvement of breast cancer apps. This study aims to critically review the quality, privacy, and security of breast cancer apps available to Arabic speakers. Similar to several recent studies, we used a systematic search for apps available in Google Play and Apple App stores using both the web interface and the built-in native stores installed on smartphones. The search was conducted in mid-December 2022 in Arabic using the following keywords: سرطان الثدي - فحص سرطان الثدي - علاج سرطان الثدي - مرض سرطان الثدي - أعراض سرطان الثدي - فحص الثدي (breast cancer, breast cancer treatment, breast cancer disease, breast cancer symptoms, breast cancer screening, and breast test). These preidentified search terms are based on earlier work concerning the top searched breast cancer topics by Arabic speakers through Google's search engine. We excluded apps that did not have an Arabic interface, were developed for non-Arabic speakers, were paid, needed a subscription, or were directed toward health care workers. The Mobile App Rating Scale was used to evaluate the quality of the apps concerning their engagement, functionality, aesthetics, and information. A risk score was calculated for the apps to determine their security risk factors. Only 9 apps were included, with most (6/9, 67%) being supported by advertisements and categorized as informational. Overall, the apps had low numbers of downloads (>10 to >1000). The majority of the included apps (8/9, 89%) requested dangerous access permissions, including access to storage, media files, and the camera. The average security score of the included apps was 3.22, while only 2 apps provided information about data security and privacy. The included apps achieved an overall average quality score of 3.27, with individual dimension scores of 4.75 for functionality, 3.04 for information, 3.00 for aesthetics, and 2.32 for engagement. The limited availability of breast cancer apps available to Arabic speakers should be a call to action and prompt health care organizations and developers to join forces and collaboratively develop information-rich, usable, functional, engaging, and secure apps.

Camguard: Preventing unauthorised camera access for women’s saftey

Online harassment is a serious problem that can have significant negative impacts on the mental health and well-being of its victims. To address this issue, an Android app has been developed that is accessible to a wide range of users worldwide. The app is built on a script backend process, providing a stable and efficient environment for data management and request processing. The app's API is integrated into the script backend process, ensuring seamless and efficient operation.During the installation process, the app requires users to go through a verification process that includes providing their Google Account, mobile number, and an OTP. This ensures that only legitimate users have access to the app's features and functions. The app also requires users to create a strong master password, which is directly connected to the Google bot, enhancing its security. Biometrics are recommended to protect the master password, ensuring that only authorized users can access their data.The app's security measures are crucial in ensuring the privacy and protection of user data. The use of biometrics and direct connection to the Google bot enhances security, and the app's API provides access to relevant information and enhances the user experience. Users can change their password securely, ensuring that only authorized users can access their data.Overall, the app is a reliable and efficient solution for managing and protecting user data. Its compatibility with a wide range of devices and seamless integration of API make it accessible to a large percentage of Android users worldwide. The app's verification process, use of biometrics, and direct connection to the Google bot enhance its security, ensuring that only authorized users have access to the app's functionalities. The development of this app is a critical step in addressing the issue of online harassment and protecting the privacy and well-being of its users.

Measuring the Security of Indonesian Local Goverment Mobile Apps

Mobile apps are critical in supporting the Indonesian provincial government during daily operations. Regarding their important role, these apps are the potential to become a target of malicious activity to gain access to government information. Hence, in this research, we conduct a security measurement of mobile apps affiliated with the provincial governments in Indonesia, aiming to provide a source of information for the app's developer to make further security improvements. To the best of our knowledge, this is the first study to conduct an empirical analysis related to this area, expecting to become a cornerstone for further research. In total, we found 162 mobile apps available on the Google Play Store and correlated to 31 province governments in Indonesia. We conducted standard mobile apps static analysis method, starting from metadata scraping of each provincial government-affiliated app available at the Google Play Store and measured their security based on several indicators, including access to sensitive permission, unprotected exported components, the adoption of binary protection mechanism, and the appearance of third-party tracker libraries. We found that 27.1% (44) government apps request at least two dangerous permission, over 5% of the apps embed the Advertisement library, 10% of the apps have more than five exported Activities, and 44 (25.94%) Indonesian government apps did not adopt any binary protection mechanism. Hence, these results can be tailored as a reference for the provincial government in determining the level of effectiveness and impact of an app when developing mobile-based software in the future.

What would it take to improve the uptake and utilisation of mHealth applications among older Australians? A qualitative study.

Objective Health-related apps on mobile devices (mHealth apps) have become an effective self-management tool and treatment support for patients. There is limited research, however, on how older people (50 and over) perceive the opportunity of using mHealth apps. Our aim was to investigate the perceptions of older people in Australia regarding the opportunity of using prescribed or doctor-recommended mHealth apps and provide insights which can enhance their uptake of mHealth. Methods This was a qualitative study using semi-structured interviews involving 21 participants aged 51-82 years. Qualitative thematic analysis was used to categorise the factors that influence the adoption of mHealth apps by older adults. Results We show that beyond the prominent influencing factors from technology adoption research (such as performance and effort expectancy, social influence and facilitating conditions), health-specific factors such as a trusting doctor-patient relationship and strong health self-efficacy positively influence the intended adoption of mHealth apps among older adults. In addition, the IT security and accurate interpretation of participants' input in an mHealth app can present barriers to mHealth app adoption. Conclusion Our analyses provide additional insights complementing existing technology adoption research. Their successful adoption and utilisation require further empirical evidence on its effectiveness along with attention to the voices of those who are meant to use them. To address potential barriers, improve the quality and security of mHealth apps, and thus achieve greater patient safety, the involvement of consumers, regulators and health professionals is necessary.

Malware Detection

The "Malware Detection on Application using Machine Learning" project is a focused initiative aimed at enhancing the security of mobile applications through advanced detection mechanisms. As the threat landscape for mobile app-based malware continues to evolve, this project leverages the power of machine learning to develop robust and adaptive detection models. The project involves the analysis of application behavior, employing both static and dynamic approaches, to identify and categorize potential malware instances. By training machine learning models on extensive datasets, the project aims to enable the detection of diverse forms of malicious software, including viruses and trojans. The integration of machine learning into the detection process facilitates continuous learning and adaptation to emerging threats. Keywords: Malware Detection, Machine Learning, Mobile Applications, Security Enhancement, Threat Landscape, Behavioral Analysis, Static Analysis, Dynamic Analysis, Virus Detection, Trojan Detection, Adaptive Models, Continuous Learning, Emerging Threats, Proactive Defense, Mobile App Security.

Sickle Cell Disease Education in Low and Middle Income Countries Using a Smartphone Clinical Case Discussion App

Introduction Sickle cell disease (SCD) is one of the world's most common hemoglobinopathies, affecting over 400,000 newborns annually (Archer et al., 2022). Despite the World Health Organisation's (WHO) 2006 long-term goals to address the SCD burden, the disease's mortality, particularly within low- and middle-income countries (LMICs) such as India and Sub-Saharan Africa (SSA), remains high (WHO 2006). Barriers to improving outcomes for SCD patients in LMICs include a lack of awareness around treatment guidelines and inadequate clinical knowledge among healthcare professionals (HCPs). While effective medical education programs are essential to the provision of high-quality healthcare services, the delivery of such programs in LMICs is challenging due to limited budgets, poor training infrastructure and equipment, and insufficient educators (Barteit et al., 2020). Recently, consideration has been given to the role that digital learning platforms could play in supporting medical education in LMICs (Nicoll et al., 2018). Aim To assess the impact of a smartphone app delivered medical education program in improving HCP clinical knowledge around SCD in LMICs, focused on SSA (Kenya, Ghana, Zambia, Uganda,Tanzania) and India. Methods The SCD program was developed by subject matter experts with MedShr, a secure app- and web-based clinical case discussion platform freely accessible to HCPs worldwide. The program's focus was determined at the outset through a needs-based approach. Analysis of MedShr's proprietary data enabled the identification of key knowledge gaps among HCPs that could be addressed with case-based education, forming the basis for three themes: 1) Acute SCD presentations 2) Chronic SCD complications 3) Long-term SCD management 9 clinical cases comprising a patient vignette, open question and integrated poll were developed by MedShr in line with the program themes. A case example is displayed in Figure 1. Content delivery via the MedShr platform was from August 2022 to February 2023, during which time the cases were promoted to relevant HCPs via email, push notifications and social media. All content was featured within a SCD Global Education Network group on MedShr, connecting target HCPs and facilitating peer-to-peer discussion. Results During the 6 month program, over 173,000 HCPs were reached globally with the educational content, including 75,070 clinicians in SSA and 64,210 in India. HCPs reached included community health workers (28%), GPs (24%), acute physicians (16%), emergency physicians (32%), pediatricians (13%), hematologists (3%), and nurses (8%). The program achieved over 73,000 engagements (case follows, likes, votes and comments) from target HCPs, including 26,419 engagements from HCPs in SSA and 11,173 from those in India. Stand-alone poll questions aligned to the three educational themes were implemented pre- and post-program delivery to assess the program's educational impact. An improvement in clinician knowledge was demonstrated across all three themes (Figure 2). Participant surveys were also used to determine the program's impact on HCP knowledge and clinical behaviors. 84% of participants deemed the content ‘very valuable’ to their clinical decision-making, while 90% stated that they had implemented knowledge obtained from the program in clinical practice. Conclusions The SCD program delivered via the MedShr smartphone app provided a low-cost, high-impact mechanism to deliver effective medical education in LMICs. MedShr's unique SCD professional network provides a digital interface for HCPs, through which peer engagement, interactive discussion and sharing feedback drive learning and behavioral change. The program's metrics highlight the potential scale for digital learning platforms to reach and engage HCPs across diverse geographies, and the program polling and participant surveys demonstrate impact, and that there is scope to improve HCPs' knowledge and practice without costly face-to-face education. Future work should aim to develop tailored learning programs designed to fit local contexts in LMICs, and explore the use of technology-based learning programs in other commonly encountered disease areas. The educational program was funded by an unrestricted educational grant from Novartis. Novartis had no input into content development and their employees could not access the MedShr platform or members.

MDSSED: A safety and security enhanced model-driven development approach for smart home apps

With the popularization of smart home devices, people rely more on automation functions provided by smart home apps. This increases the attack surface for safety and security threats. Many of these threats are at the interaction level, caused by unintended or malicious interactions between apps. Most of the current studies focus on identifying unsafe interactions between smart home apps by code analysis. To the best of our knowledge, none of the existing studies focuses on enhancing the safety and security of smart home apps under interaction threats in the design phase. To fill this gap, this paper presents MDSSED, a safety and security enhanced model-driven development approach for smart home apps. First, this paper identifies eleven types of interaction threats faced by smart home apps. Second, the MDSSED profile is proposed to support modeling smart home apps using UML. Third, the MDSSED prototype tool is developed to generate threat models and corresponding safety and security properties automatically. Then, the safety and security properties are automatically verified by model checking. Finally, the MDSSED tool automatically converts the UML models to the Samsung SmartThings apps. To evaluate the accuracy and effectiveness of MDSSED, this paper uses the benchmarks in existing state-of-the-art studies. The results show that MDSSED not only identified the safety and security problems in the existing benchmarks but also pointed out vulnerabilities of apps under other interaction threats identified in this paper. To the best of our knowledge, MDSSED is the first model-driven development approach that supports the automatic verification of the safety and security properties of smart home apps under interaction threats. The accuracy, practicality, and efficiency of MDSSED are corroborated by experiments. The source code of the MDSSED tool and the experimental data are available online.1

People identification via tongue print using fine-tuning deep learning

<span>Many person-verification systems are critical in security systems for verifying passage through doors opened to specific people using various techniques. People can use electronic payment methods and security apps to generate codes for quick, remote financial transactions. Older systems required precision and speed. Many alternative methods were developed by technology and artificial intelligence to make such operations simple and quick. The identification of tongue prints is discussed in this paper. Tongue prints, like fingerprints, are unique to each individual. The tongue was used in this study because it is unique among such organs. The tongue is protected by the lips. This guards against taking a tongue print by force. Some people distort their fingerprints, making fingerprint recognition systems unable to recognize them. Car accidents cause facial distortion, which distorts the system and prevents it from distinguishing facial prints, so the tongue was used as a fingerprint in this study. A database of 1,104 images for 138 Mustansiriyah University College of Science students yielded an average of eight images per individual. VGG16 was implemented for transfer learning and fine-tuning. In comparison to previous studies, the accuracy achieved was more than 91%.</span>