Fake Users Research Articles

Detection of spam-posting accounts on Twitter

Abstract Online Social Media platforms, such as Facebook and Twitter, enable all users, independently of their characteristics, to freely generate and consume huge amounts of data. While this data is being exploited by individuals and organisations to gain competitive advantage, a substantial amount of data is being generated by spam or fake users. One in every 200 social media messages and one in every 21 tweets is estimated to be spam. The rapid growth in the volume of global spam is expected to compromise research works that use social media data, thereby questioning data credibility. Motivated by the need to identify and filter out spam contents in social media data, this study presents a novel approach for distinguishing spam vs. non-spam social media posts and offers more insight into the behaviour of spam users on Twitter. The approach proposes an optimised set of features independent of historical tweets, which are only available for a short time on Twitter. We take into account features related to the users of Twitter, their accounts and their pairwise engagement with each other. We experimentally demonstrate the efficacy and robustness of our approach and compare it to a typical feature set for spam detection in the literature, achieving a significant improvement on performance. In contrast to prior research findings, we observe that an average automated spam account posted at least 12 tweets per day at well defined periods. Our method is suitable for real-time deployment in a social media data collection pipeline as an initial preprocessing strategy to improve the validity of research data.

CTD: Fast, accurate, and interpretable method for static and dynamic tensor decompositions.

How can we find patterns and anomalies in a tensor, i.e., multi-dimensional array, in an efficient and directly interpretable way? How can we do this in an online environment, where a new tensor arrives at each time step? Finding patterns and anomalies in multi-dimensional data have many important applications, including building safety monitoring, health monitoring, cyber security, terrorist detection, and fake user detection in social networks. Standard tensor decomposition results are not directly interpretable and few methods that propose to increase interpretability need to be made faster, more memory efficient, and more accurate for large and quickly generated data in the online environment. We propose two versions of a fast, accurate, and directly interpretable tensor decomposition method we call CTD that is based on efficient sampling method. First is the static version of CTD, i.e., CTD-S, that provably guarantees up to 11× higher accuracy than that of the state-of-the-art method. Also, CTD-S is made up to 2.3× faster and up to 24× more memory-efficient than the state-of-the-art method by removing redundancy. Second is the dynamic version of CTD, i.e. CTD-D, which is the first interpretable dynamic tensor decomposition method ever proposed. It is also made up to 82× faster than the already fast CTD-S by exploiting factors at previous time step and by reordering operations. With CTD, we demonstrate how the results can be effectively interpreted in online distributed denial of service (DDoS) attack detection and online troll detection.

Separation of Genuine and Fake Users From e-Commerce Site Using Hybrid Learning Approach

Separation of Genuine and Fake Users From e-Commerce Site Using Hybrid Learning Approach

Detection of Fake Users Account Based on Review

Detection of Fake Users Account Based on Review

Preventing malicious accounts based on mining with steganography in online

On-line Social Networks (OSNs) are progressively exerting consequences on the way communication takes place among people through sites such as Twitter, Facebook, Google+ and LinkedIn, possessing millions of users. The Online Social Networks’ (OSN) users face security-privacy threats such as Profile cloning, privacy breach and malware attacks. By these attacks, the fake user steals the virtual identity of the original user which they use to interact with other online users. To prevent these attacks, the proposed system uses Steganography which is the process of hiding information within other non-secret text or data. Our proposed system utilizes Steganography by implementing Watermarking technique which hides a secret text inside an image invisibly. Moreover the system avoids the leakage of personal information and prevents the creation of fake accounts. Experimental results show that the proposed technique can effectively detect and prevent creating malicious accounts in comparison with the techniques reported previously.

Efficient Data Security for Mobile Instant Messenger

Instant Messenger (IM) becomes one of the most popular applications in mobile technology and communication. A lot of users around the world installed it for daily activities. Current IM found security lacks both in authentication and encryption matters. Various IM growing today still not apply an efficient method in authentication and encryption process, conventional security methods and client-server architecture system have to risk too many users for attacking server such as compromising, cracking password or PINs by Unauthorized people. Common IM services lack native encryption to protect information being transmitted over the public network and still used high computation in the mobile environment, this problem needs efficient security methods. Then, in public IM also found various messages with fake users, it occurs because public IM carry out the separate system in authentication and encryption process, strong authentication need to solve this issue in messenger environment. The tremendous growth of mobile IM user needs efficient and secure communication way. This paper proposes a new efficient method for securing message both in encryption and authentication within the end-to-end model. In this research, security method proposes new algorithms based on Elliptic Curve (EC) works in Peer to Peer (P2P) architecture than a conventional client-server model. The result shows this method produces efficient time in authentication and encryption process while applying in a mobile environment. Besides, it is compatible with the mobile phone which has a limitation of computation capabilities and resources.

Disease Risk Prediction using SVM based on Geographical Location

Nowadays, people get more useful information from the internet and other technological platforms like social media. Plenty of health-care related information is available in social media where people spend more time in it. The existing methodology doesn’t include location in particular the user similarity based on the attributes. The proposed method specifies the assessment of disease risk by Support Vector Machine (SVM) algorithm to identify the similarity between the users based on the geographical location and then recommends the health expert to the users. This method also identifies the fake users and validates them. The health-care associated with big-data can be performed effectively in the proposed framework. The experimental output shows that the proposed method is more effective when compared with Collaborative Filtering based Disease Risk Assessment.

Spatial Dissemination of Trends Along with Resolution of Multifaceted Entities

Social media is the most used medium in this digitized world to connect to the community by just a click. The users on the network can be real or fake and determining them is a challenge. User’s reaction to a topic makes it a trend and if some company, individual, organization try to analyze the users for their benefits then the whole concept of social connection and contribution is gone. So determining the real user and fake users is very important. On first level of scanning the user account may look like being legitimate but it may be not. For effective decision making in key marketing strategies for a particular location, the demographics and the numbers should be perfect for better results. Hence, many-fold improves the spatial dissemination that is being done by filtering the fake users in the online community.

Generic anomalous vertices detection utilizing a link prediction algorithm

In the past decade, graph-based structures have penetrated nearly every aspect of our lives. The detection of anomalies in these networks has become increasingly important, such as in exposing infected endpoints in computer networks or identifying socialbots. In this study, we present a novel unsupervised two-layered meta-classifier that can detect irregular vertices in complex networks solely by utilizing topology-based features. Following the reasoning that a vertex with many improbable links has a higher likelihood of being anomalous, we applied our method on 10 networks of various scales, from a network of several dozen students to online networks with millions of vertices. In every scenario, we succeeded in identifying anomalous vertices with lower false positive rates and higher AUCs compared to other prevalent methods. Moreover, we demonstrated that the presented algorithm is generic, and efficient both in revealing fake users and in disclosing the influential people in social networks.

Security Enhancement of Fix Chaotic-DSSS in WSNs

The security of the physical layer promises to provide secrecy for wireless communication. The chaotic direct sequence spread spectrum (chaotic-DSSS) is one of the distinguished techniques for providing secrecy in wireless communication. However, conventional chaotic-DSSS requires chip synchronization which makes this system complex to implement in wireless sensor networks (WSNs). This letter suggests using a fix chaotic-DSSS and also proposes a new method, called fake users , to enhance the security of the chaotic-DSSS based WSNs. The performance of the proposed method is theoretically investigated and validated through simulation. The results suggest that the proposed method can significantly improve the security of WSNs.

Audit-Free Cloud Storage via Deniable Attribute-Based Encryption

Cloud storage services have become increasingly popular. Because of the importance of privacy, many cloud storage encryption schemes have been proposed to protect data from those who do not have access. All such schemes assumed that cloud storage providers are safe and cannot be hacked; however, in practice, some authorities (i.e., coercers) may force cloud storage providers to reveal user secrets or confidential data on the cloud, thus altogether circumventing storage encryption schemes. In this paper, we present our design for a new cloud storage encryption scheme that enables cloud storage providers to create convincing fake user secrets to protect user privacy. Since coercers cannot tell if obtained secrets are true or not, the cloud storage providers ensure that user privacy is still securely protected.

Discovering spammer communities in twitter

Online social networks have become immensely popular in recent years and have become the major sources for tracking the reverberation of events and news throughout the world. However, the diversity and popularity of online social networks attract malicious users to inject new forms of spam. Spamming is a malicious activity where a fake user spreads unsolicited messages in the form of bulk message, fraudulent review, malware/virus, hate speech, profanity, or advertising for marketing scam. In addition, it is found that spammers usually form a connected community of spam accounts and use them to spread spam to a large set of legitimate users. Consequently, it is highly desirable to detect such spammer communities existing in social networks. Even though a significant amount of work has been done in the field of detecting spam messages and accounts, not much research has been done in detecting spammer communities and hidden spam accounts. In this work, an unsupervised approach called SpamCom is proposed for detecting spammer communities in Twitter. We model the Twitter network as a multilayer social network and exploit the existence of overlapping community-based features of users represented in the form of Hypergraphs to identify spammers based on their structural behavior and URL characteristics. The use of community-based features, graph and URL characteristics of user accounts, and content similarity among users make our technique very robust and efficient.

Identifying Fake News and Fake Users on Twitter

In the last years big social networks like Facebook or Twitter admit that on their networks are fake and duplicate accounts, fake news and fake likes. With these accounts, their creators can distribute false information, support or attack an idea, a product, or an election candidate, influencing real network users in making a decision. In this paper, we present our system build with the aim of identifying fake users and fake news in the Twitter social network.

An empirical approach for fake user detection in location-based social networks

An empirical approach for fake user detection in location-based social networks

Trust Aware System for Social Networks: A Comprehensive Survey

Social networks are the platform for the users to get connected with other social network users based on their interest and life styles. Existing social networks have millions of users and the data generated by them are huge and it is difficult to differentiate the real users and the fake users. Hence a trust worthy system is recommended for differentiating the real and fake users. Social networking enables users to send friend requests, upload photos and tag their friends and even suggest them the web links based on the interest of the users. The friends recommended, the photos tagged and web links suggested may be a malware or an untrusted activity. Users on social networks are authorised by providing the personal data. This personal raw data is available to all other users online and there is no protection or methods to secure this data from unknown users. Hence to provide a trustworthy system and to enable real users activities a review on different methods to achieve trustworthy social networking systems are examined in this paper.

Profile characteristics of fake Twitter accounts

In online social networks, the audience size commanded by an organization or an individual is a critical measure of that entity’s popularity and this measure has important economic and/or political implications. Such efforts to measure popularity of users or exploit knowledge about their audience are complicated by the presence of fake profiles on these networks. In this study, analysis of 62 million publicly available Twitter user profiles was conducted and a strategy to identify automatically generated fake profiles was established. Using a combination of a pattern-matching algorithm on screen-names and an analysis of update times, a reasonable number (∼0.1% of total users) of highly reliable fake user accounts were identified. Analysis of profile creation times and URLs of these fake accounts revealed their distinct behavior relative to a ground truth data set. The characteristics of friends and followers of users in the two data sets further revealed the very different nature of the two groups. The ratio of number of followers-to-friends for ground truth users was ∼1, consistent with past observations, while the fake profiles had a median ratio ∼30, indicating that the fake users we identified were primarily focused on gathering friends. An analysis of the temporal evolution of accounts over 2 years showed that the friends-to-followers ratio increased over time for fake profiles while they decreased for ground truth users. Our results, thus, suggest that a profile-based approach can be used for identifying a core set of fake online social network users in a time-efficient manner.

Proof of Retrievability in Cloud Computing Environment using Sharing of Key based on Resource

The storage and retrieval of data over cloud computing is big issue. For the storage and retrieval cloud computing used the concept of authentication and authorization. The process of authentication and authorization used primary and secondary authentication system. In primary authentication system used login id and password, in secondary login used the OTP and some other verification code. In both login systems trap the OTP code and primary information of user and the security process of cloud environment are compromised. In this paper proposed a model of secured access based on the concept of fake and genuine user. In the case of fake user the received file is fake. This file is generated by the system. For the authentication of genuine and fake user used the concept of shared key concept. The shared key gives the option of retrieval of data over cloud environment. The proposed model implemented in java software and used java RMI tool for access of remote machine. General Terms Cloud Computing, Data Dynamics, Proof of Retrievability.

MASQUERADE DETECTION USING IMPROVED SEMI GLOBAL POSITIONING ALGORITHM

A masquerade attack is an attack that uses a fake identity, such as a network identity to gain unauthorized access to personal computer information. The semi-global positioning algorithm (SGA) is one of the most dynamic ways to find these type of Sybil(fake user) attacks, but it has not stretch the target and executions as expected by multi user systems. However, the problem of false positive and false negative rate have not been reduced to as expected. To improve both the effectiveness and the performances of the SGA method, we are proposing Improved SGA, ISGA approach. ISGA improves the marking systems. ISGA even allows a little change in the user command. It as well makes suitable changes in the user behavior by upgrading the signature of the user according to the current behavior. After describing about ISGA, we represent the experimental results, the result shows that the ISGA gets the hit ratio of 90 percent and above with a low false positive rate. It increases the hit ratio by about 21.9 percent. Hence, ISGA results in increasing hit ratio.

An AP-Based Shilling Attack Detector for Collaborative Recommender Systems

Collaborative filtering is a technique widely used in online recommender systems nowadays. However, it is vulnerable from manipulation by malicious users who often create some fake account (or shilling) profiles to influence the results of recommender systems. To identify the fake users, existing algorithms usually utilize certain characteristics of shilling profiles, of which the drawback is the low precision and the requirement of a large size of training set. In this paper, we develop a clustering based method to find the shilling attackers by incorporating the information of user ratings and the attribute of user profiles. The users are firstly self-organizedly clustered into several groups based on the integrated information of the rating features and the attributes of user profile, then the malicious user group is identified through the GRDMA values of user group. Instead of identifying attacker one by one, the proposed algorithm finds the malicious users at the collective level, which providing a novel way to analyze and detect shilling attack. The experimental results performed on MovieLens datasets demonstrate that the proposed algorithm is effective and robust in three typical kinds of shilling attack models, especially when the attack size and the filler size are sufficiently high.

Online Guessing Attacks – A Prevention using PGRP and PCCP

Background: Cryptanalytic attacks like Brute Force and Dictionary Attacks over password-only remote login services are widespread now-a-days. The major challenge is to allow the genuine users to login by preventing such attacks. Method: PGRP (Password Guessing Resistant Protocol) and PCCP (Persuasive Cued Click Points). Results: It gives a security mechanism for preventing the fraudulent user from using the system and also tries to identify the details of fake user. Application: User Authentication Based Systems