No abstract

On social platforms like Facebook, it is popular and pleasurable to share photos among friends, but it also puts other participants in the same picture in jeopardy when the photos are released online without the permission from them. To solve this problem, recently, the researchers have designed some fine-grained access control mechanisms for photos shared on the social platform. The uploader will tag each participant in the photo, then they will receive internal messages and configure their own privacy control strategies. These methods protect their privacy in photos by blurring out the faces of participants. However, there is still some defect in these strategies due to the unpredictable tagging behaviors of the uploader. Malicious users can easily manipulate unauthorized tagging processes and then publish the photos, which the participants want them to be confidential in social media. To address this critical problem, we propose a participant-free tagging system for photos on social platforms. This system excludes potential adversaries through automatic tagging processes over two cascading stages: 1) an initialization stage will be applied to every new user to collect his/her own portrait samples for future internal searching and tagging, and; 2) the remaining unidentified participants will be tagged in cooperative tagging stage by the users who have been identified in the first stage. For the system evaluation of efficiency and effectiveness, we conducted a series of experiments. The results demonstrated the tagging efficiency (96% tagging rate and 0.77s/photo tagging speed on average), photo masking and unmasking efficiency (0.13s/face on average), and the privacy preserving performance (over 90% identities in both group and individual photo are preserved).INDEX TERMS Social media, face tagging, privacy protection, system security.

No abstract

Online social networks (OSNs) are a rich source of information, and the data (including user-generated content) can be mined to facilitate real-world event prediction. However, the dynamic nature of OSNs and the fast-pace nature of social events or hot topics compound the challenge of event prediction. This is a key limitation in many existing approaches. For example, our evaluations of six baseline approaches (i.e., logistic regression latent Dirichlet allocation based logistic regression, multitask learning, long short-term memory and convolutional neural networks, and transformer-based model) on three datasets collected as part of this research (two from Twitter, and one from a news collection site 1 ), reveal that the accuracy of these approaches is between \(50\% \) and \(60\% \) , and they are not capable of utilizing new events in event predictions. Hence, in this paper we develop a novel DNN-based framework (hereafter referred to as event prediction with feedback mechanism – EPFM . Specifically, EPFM makes use of a feedback mechanism based on emerging events detection to improve the performance of event prediction. The feedback mechanism ensembles three outlier detection processes and returns a list of new events. Some of the events will then be chosen by analysts to feed into the fine-tuning process to update the predictive model. To evaluate EPFM, we conduct a series of experiments on the same three datasets, whose findings show that EPFM achieves \(80\% \) accuracy in event detection and outperforms the six baseline approaches.We also validate EPFM’s capability of detecting new events by empirically analyzing the feedback mechanism under different thresholds.

Computer users are generally faced with difficulties in making correct security decisions. While an increasingly fewer number of people are trying or willing to take formal security training, online sources including news, security blogs, and websites are continuously making security knowledge more accessible. Analysis of cybersecurity texts from this grey literature can provide insights into the trending topics and identify current security issues as well as how cyber attacks evolve over time. These in turn can support researchers and practitioners in predicting and preparing for these attacks. Comparing different sources may facilitate the learning process for normal users by creating the patterns of the security knowledge gained from different sources. Prior studies neither systematically analysed the wide range of digital sources nor provided any standardisation in analysing the trending topics from recent security texts. Moreover, existing topic modelling methods are not capable of identifying the cybersecurity concepts completely and the generated topics considerably overlap. To address this issue, we propose a semi-automated classification method to generate comprehensive security categories to analyse trending topics. We further compare the identified 16 security categories across different sources based on their popularity and impact. We have revealed several surprising findings as follows: (1) The impact reflected from cybersecurity texts strongly correlates with the monetary loss caused by cybercrimes, (2) security blogs have produced the context of cybersecurity most intensively, and (3) websites deliver security information without caring about timeliness much.