Currently, the rapid popularity of social network platforms makes the real social relations in social networks face the potential risk of disclosure. Therefore, most users may refuse to provide their social relations for the purpose of privacy preservation, which is not conducive to the development of social networks. The negative survey is an emerging sensitive information collection method, which can collect sensitive information while preserving personal privacy. In this paper, based on negative survey, we propose an algorithm called NetNS to preserve the privacy of social relations, namely the topology privacy of social networks. The proposed NetNS is simple and efficient, which only randomly divides the nodes in social networks into different groups, and disturbs the topology of each group by a dedicated negative survey model. Experiments are carried out on three real networks of different sizes. The experimental results show that compared to three algorithms tailored for topology privacy of social networks, the proposed NetNS can against graph structure attack while realizing better utility of social networks.
Nowadays, the internet is used by billions of users around the world for many different purposes, some of which require user identity authentication. To face the challenge of reliable authentication, researchers have proposed various techniques, ranging from face recognition to fingerprints. The aim of this study is to develop a PPG/ECG-based (Photoplethysmography/Electrocardiogram) user identity authentication approach using features extracted by recurrence quantification analysis (RQA). The PPG/ECG signal is segmented into frames and thirteen features are obtained using RQA. These features are then fed into four classifiers for user identity authentication purposes: linear discriminant analysis, support vector machine, naïve Bayes, and random forest. The best result obtained using this methodology is an average accuracy of 99.48% achieved using a random forest classifier with frame length of three seconds.
While the Cost-Per-click mechanism ensures the prosperity of the mobile advertising ecosystem, click fraud becomes a significant threat that results in huge losses for advertisers. On the one hand, some existing studies identify click fraud in a predefined test environment on the client side. However, these works neglect the influence of user interaction on fraudulent behaviours. On the other hand, some studies employ binary classifiers to detect click fraud on the server side without considering the particularity of the click fraud scenario. This paper presents the design and implementation of CFDMA, a click fraud detection system that conducts both server side and client side detection. CFDMA makes connections between fraudulent behaviours and explicit user inputs through observing sensitive system classes on the client side. CFDMA constructs the publisher graph on the server side and uses its information to detect invalid traffic. We evaluate the performance of CFDMA on real click datasets. Our evaluation demonstrates that CFDMA is capable of identifying invalid click traffic and fraudulent behaviours.
This paper describes a method of secure authentication using FIDO2 security keys with VPN systems based on legacy protocols by leveraging a dedicated web-based VPN portal and allowing to implement a Passwordless access method.
In pracyical life scene, most access control systems (ACS) cannot solve the problem of various sproofing ways and mask-wearing recognition. In this paper, a new security classification framework based on face recognition is proposed. This framework uses face recognition algorithm with anti-spoofing function. In order to evaluate the performance of the framework, this paper employs the Chinese Academy of Science Institute of Automation-Face Anti-spoofing Datasets (CASIA-FASD) as benchmarks. Performance evaluation indicates that the Half Total Error Rate (HTER) is 9.7%, the Equal Error Rate (EER) is 5.5%. The results demonstrate that this framework has a high anti-spoofing capability and can be employed on the embedded system to complete the mask detection in real-time.
