Short URLs Research Articles

Phishing URL detection with neural networks: an empirical study

Cybercriminals create phishing websites that mimic legitimate websites to get sensitive information from companies, individuals, or governments. Therefore, using state-of-the-art artificial intelligence and machine learning technologies to correctly classify phishing and legitimate URLs is imperative. We report the results of applying deterministic and probabilistic neural network models to URL classification. Key achievements of this work are: (1) The development of a unique approach based on probabilistic neural networks that improves classification accuracy. (2) We show for the first time in URL phishing research that a machine learning model trained on a combination of open source and private datasets is successful in production. The dataset is constructed from open sources like Alexa, PhishTank, or OpenPhish and, most importantly, real-world production data from EasyDMARC. The daily validation of the model using daily reported URL data and corresponding labels, both from open-source platforms and private production, reach on average a 97% accuracy on the validation dataset, labeled by PhishTank, OpenPhish and EasdDMARC where possible mislabeled data can not be excluded and was not possible to check due to large number of URLs. Feature engineering was done without third-party dependencies. Lastly, the evaluation of both deterministic and probabilistic models shows high accuracy on short and long URLs, where short URLs are defined as having less than 50 characters.

URL shortener for web consumption: an extensive and impressive security algorithm

<p>URL stands for uniform resource locator are the addresses of the unique resources on the internet. We all need URLs to access any type of resource on the internet, such as any web page, and document. Sometimes URLs can be long, irrelative and unattractive and unable to send sometimes via email. So, for this, we proposed a URL shortener web application based on the Python-Django platform which is fast and makes your long URLs in the shortest form which you can share on social media platforms. It makes all the messy, unattractive URLs short and shareable. Writing paper proposed a premium section in our application that gives access to the customizable URLs and analytics of your shorten URLs. Customizable URLs are the URLs you create by your own keywords. By creating a premium profile with the application, you can create your own URLs by using your own keywords. We have considered security a major part of the application that prevents the short URLs from being hacked or redirected to any advertising website or content. We store all the data related to the URL to show you the best view of your analytics and update it regularly. Main contribution in this field that for web application that provides users with a fast, secure and shortest URL for their using long URLs. Comparatively to other services that are currently available, the application provides superior security, availability, and confidentiality.</p>

Ensemble Learning-Based Browser Extension for Mitigating Cyber Attacks Carried out using Malicious Short URLs

As digitization continues to expand and cybercrimes become more prevalent, making it is crucial to prioritize the implementation of robust security measures. Malicious short URLs are frequently utilized as a vector for cyber-attacks on online forums and social media platforms. To address this issue, a plugin-based solution that uses ensemble learning to combine random forest, k-neighbors classifier, and logistic regression into a stacked model, was developed. The model was trained over the combination of three most popular kaggle datasets, with over 1081195 URLs. Additionally, gradient boosting was applied to further enhance the model's performance, resulting in a 92% accuracy in the detection. We developed the browser extension with Flask and JavaScript that identifies URLs as malicious or safe, for facilitation of the proposed solution. The work emphasizes the need for effective measures to mitigate cyber-attack risks, particularly those involving malicious short URLs.

Using Google Forms as an Online Learning Assessment Tool for Non-EFL Students

This research investigates the use of Google Forms as an online learning assessmenttool for non-EFL students at Institute Technology Business AAS Indonesia and toknow the strengths and limitations of Google Forms in assessing English students’learning. This is descriptive qualitative research. The method of collecting data in thisresearch used observation. The analysis shows that Google Forms is a practical,effective, and easy learning assessment tool for English lecturers in mid-term testsand final tests in English courses. We can use Google Forms by first logging into aGoogle account, making a learning assessment title, setting the initial learningassessment, deciding on question type, making questions, making answer keys anddefault scores, copying a URL link test, sharing, scoring, and analyzing the result. Wecan set a time limit for taking questions/quizzes on Google Forms so students canwork on test questions on time. Google Forms offers benefits that help us to createEnglish tests. It is free to use, easy to use, integrated with Google Sheets, can beeasily used and shared, and data presentation from respondents can be presented invarious forms, open source, saving cost, saving time and energy, storing datasecurely, integrated add-ons, having short URLs, having many choices of quiz menus,having auto-summary and real-time survey results. However, Google Forms haslimitations including limited design and font choices, limited export options only toGoogle Sheets and PDF, no email notifications, no editing/modification history, andGoogle Forms cannot be used in online discussion forums. However, the pros anddownsides of using Google Forms as an online assessment tool were not discussedin depth by the researchers. In this scenario, the researcher intends to carry out astudy on Google Forms by enrolling in the teaching site's 'English 2' course.Keywords: assessment tool, Google Form, online learning assessment

My Health My Language bridging the gap in public healthcare messaging

Abstract Issue Like many other European countries there has been a sharp increase in the number of migrants in Ireland recently. 13.9% of migrants in Ireland have poor or no English (Census 2016) and are not reached with mainstream public health messaging. Prior to the COVID-19 pandemic, most intercultural health resources were written rather than audio-visual. A clear need to reach out to these communities was identified. Project In 2021 the Health Service Executive (HSE) National Social Inclusion Office (NSIO) initiated a project with Translate Ireland (TI) to address the gap in intercultural health resources. Through consultation, priority health protection and health service areas were identified for inclusion in a suite of videos in main migrant languages. NSIO consulted with mychild.ie, National Immunisation Office, Irish College of GPs, Public Health, HSE Communications and the Sexual Health/Crisis Pregnancy Programme to ensure the scripts were aligned with HSE policy. TI identified health professionals living and working in Ireland, that were part of the migrant communities, to deliver key messages in the videos. TI worked with the presenters in wording the scripts to ensure cultural appropriateness. Results 11 primary care/maternal care videos were produced in 17 languages (187 videos), for healthcare professionals and people seeking health information. A dedicated webpage was created to ensure the videos were easily accessible and the project was named My Health My Language. The project was formally launched in June 2022 by the Minster of Health. We engaged with migrant communities, NGOs and government departments to share the multi-media video messages. By June 2023 there are 14,055 views of the videos. Lessons As smartphones are widely used by underserved groups, video messaging is very effective, for those with limited English or where English is not their first language. Short URLs on social media are very effective in providing access to videos. Key messages • My Health My Language is a health equity initiative, addressing health information needs of people who have limited English or where English is not their first language. • Culturally appropriate healthcare videos by peer healthcare professionals speaking in their own language have had significant reach, with over 14,000 views since launching in April 2022.

A URL Shortening Service by Using Flask Framework Based on Base-62 Algorithm

In this paper, we have shown the importance of URL shortening at the time of sharing on various platforms. URLs appear to be long, unattractive, on most of the social platforms. They often get broken when shared on social media platforms like e-mail and short URLs can come in handy during these times. To shorten an Internet Long URL, we proposed a URL shortening service that will take a long Web URL/address and creates a shorter URL that will not break when we share on different platforms and make them more manageable by using flask framework base62 algorithm. In this paper, we have also provided a way that helps during digital marketing, social campaigning, and posting by giving the stats of the number of clicks made to the shortened URL as it shows the number of people interested in clicking the URL.

Understanding Security Risks of Ad-based URL Shortening Services Caused by Users' Behaviors

URL shortening services enable us to shorten or simplify URLs. Ad-based URL shortening services display advertisements to users who access short URLs and reward short URL creators. However, ad-based URL shortening services have specific security risks that URL shortening services without ads do not, such as displaying malicious advertisements to users. In this study, we reveal previously unknown security risks of these services caused by users' behaviors. We conducted a comprehensive measurement of ad-based URL shortening services. First, we accessed short URLs of these services, clicked buttons on the web pages, and reached the final destinations of the short URLs. Then, we reveal the security risks posed to users by monitoring and analyzing traffic logs when such short URLs are accessed. We found that all services generated an average of 86.5 web requests to malicious domain names per short URL. We then showed the security risk of unintentionally communicating malicious domain names even when users click only on buttons that correctly move users to their desired destinations. Finally, we discuss countermeasures to mitigate these risks from the perspective of each stakeholder in ad-based URL shortening services.

Optimised URL Shortener using Cloud Platform

Short URLs have become commonplace. Short URLs, which are especially popular in social networking services, have witnessed a significant increase in their use in recent years, largely due to Twitter's restriction on message length to 140 characters. We рrоvidе a first сhаrасterizаtiоn in the usage of short URLs in this рарer. Our specific goal is to create a system architecture for short URLs and have an optimized solution of how to use them and as well as their potential impact on web performance. Our project is made while keeping in mind that the generated URL has to be one third the size of a given url. This allows the user the functionality to share the URL with multiple individuals. Our system also incorporates the idea of tracking each individual shortened URL by the usage of a short code. It gives the user the control over their generated URLs.

P076: Do QR codes effectively engage patients in research while visiting the emergency department?

Introduction: Efforts to engage patients in research when presenting to emergency departments (EDs) have explored the utility of online tools; for example, through QR-based applications. It is unclear whether these are effective strategies for engaging patients in research activities while saving costs of in-person surveys. This study evaluated whether patients would participate in QR codes or short URL-linked surveys available in EDs across Alberta. Methods: A patient waiting room poster was developed as part of a stepped-wedge randomized controlled trial. The waiting room poster was introduced in 15 urban and regional Alberta EDs with a median annual volume of approximately 60,000. A QR-code and short URL were placed on the poster inviting patients to participate in an online survey and evaluate the poster's usefulness and acceptability. Additionally, written discharge instructions, which were part of the intervention materials, were distributed with QR-code and short URL link to surveys for patients to share their ED care experience. Patients were not prompted by any staff or research personnel to encourage use of the QR codes or the short URLs; however, a survey was conducted with ED waiting room patients in 3 urban EDs to ascertain whether they had downloaded a QR reader on their devices and the frequency of use of these applications. Results: Given the stepped-wedge nature of the study, these materials were available for a total of approximately 123 months (3 sites for 13 months, 4 sites for 10 months, 4 sites for 7 months, and 4 sites for 4 months). Over the study period, 15 patients accessed and completed the online survey linked to the QR code or the short URL placed on the posters. No patients completed the online surveys linked to the QR code or the short URL placed on the discharge instructions. The in-person survey conducted within the ED waiting room identified that 34% of respondents had a QR code reader downloaded on their phone (108/316). Of those with a QR reader, 33% reported using the reader at least once within the last 6 months. Conclusion: In this study, few patients downloaded QR readers on their electronic devices while in the ED waiting room. Without prompting, this appears to be an ineffective strategy for engaging patients in emergency medicine research. Other engagement strategies optimizing human resource investment are urgently needed to effectively conduct research in EDs.

Bit.ly/practice: Uncovering content publishing and sharing through URL shortening services

It becomes the norm for people to share online content such as images, videos, and news over various channels including online social networks, news media, or online communities. One of the popular ways to publish and share online content is using a URL shortening service, which provides a short equivalent URL that is redirected to an original URL of content. This paper comprehensively analyze the practice of using short URLs from their creations to publishing to sharing, using a large scale dataset that contains 4.2 B requests for 80 M URLs created through Bit.ly, one of the most popular URL shortening services. We find that content URLs are mosunknown.

"When 'Bad' is 'Good'": Identifying Personal Communication and Sentiment in Drug-Related Tweets.

BackgroundTo harness the full potential of social media for epidemiological surveillance of drug abuse trends, the field needs a greater level of automation in processing and analyzing social media content.ObjectivesThe objective of the study is to describe the development of supervised machine-learning techniques for the eDrugTrends platform to automatically classify tweets by type/source of communication (personal, official/media, retail) and sentiment (positive, negative, neutral) expressed in cannabis- and synthetic cannabinoid–related tweets.MethodsTweets were collected using Twitter streaming Application Programming Interface and filtered through the eDrugTrends platform using keywords related to cannabis, marijuana edibles, marijuana concentrates, and synthetic cannabinoids. After creating coding rules and assessing intercoder reliability, a manually labeled data set (N=4000) was developed by coding several batches of randomly selected subsets of tweets extracted from the pool of 15,623,869 collected by eDrugTrends (May-November 2015). Out of 4000 tweets, 25% (1000/4000) were used to build source classifiers and 75% (3000/4000) were used for sentiment classifiers. Logistic Regression (LR), Naive Bayes (NB), and Support Vector Machines (SVM) were used to train the classifiers. Source classification (n=1000) tested Approach 1 that used short URLs, and Approach 2 where URLs were expanded and included into the bag-of-words analysis. For sentiment classification, Approach 1 used all tweets, regardless of their source/type (n=3000), while Approach 2 applied sentiment classification to personal communication tweets only (2633/3000, 88%). Multiclass and binary classification tasks were examined, and machine-learning sentiment classifier performance was compared with Valence Aware Dictionary for sEntiment Reasoning (VADER), a lexicon and rule-based method. The performance of each classifier was assessed using 5-fold cross validation that calculated average F-scores. One-tailed t test was used to determine if differences in F-scores were statistically significant.ResultsIn multiclass source classification, the use of expanded URLs did not contribute to significant improvement in classifier performance (0.7972 vs 0.8102 for SVM, P=.19). In binary classification, the identification of all source categories improved significantly when unshortened URLs were used, with personal communication tweets benefiting the most (0.8736 vs 0.8200, P<.001). In multiclass sentiment classification Approach 1, SVM (0.6723) performed similarly to NB (0.6683) and LR (0.6703). In Approach 2, SVM (0.7062) did not differ from NB (0.6980, P=.13) or LR (F=0.6931, P=.05), but it was over 40% more accurate than VADER (F=0.5030, P<.001). In multiclass task, improvements in sentiment classification (Approach 2 vs Approach 1) did not reach statistical significance (eg, SVM: 0.7062 vs 0.6723, P=.052). In binary sentiment classification (positive vs negative), Approach 2 (focus on personal communication tweets only) improved classification results, compared with Approach 1, for LR (0.8752 vs 0.8516, P=.04) and SVM (0.8800 vs 0.8557, P=.045).ConclusionsThe study provides an example of the use of supervised machine learning methods to categorize cannabis- and synthetic cannabinoid–related tweets with fairly high accuracy. Use of these content analysis tools along with geographic identification capabilities developed by the eDrugTrends platform will provide powerful methods for tracking regional changes in user opinions related to cannabis and synthetic cannabinoids use over time and across different regions.

Predicting User Influence in Social Media

Understanding influence plays a vital role in enhancing businesses operation and improving effect of information propagation. Therefore the user influence in social media, such as Twitter, is widely studied based on different standards, such as the number of followers, retweets and so on. However, little work considers the accurate click number of short URLs as the measurement of influence. In Twitter short URLs are frequently included in tweets because of the limitation of characters. And some users may focus more on click number of the URLs instead of the number of followers or retweets. Thus, it is necessary to analyze the factors that impact the click number received by URLs of users. In this paper, we conduct the predictive analyses about the user influence which is measured by the click number of short URLs. We first exploit a wide range of possible features consisting of the sets of user properties, behavior and topics. And then we employ the logistic regression analysis to identify the significant features for predicting the user influence, and find most of features we proposed have a significant predictive power to the user influence. Finally based on the large scale Twitter data, four models are used for the prediction and the Bagging model achieves the best result, an overall accuracy of more than 82%.