Fake Users Research Articles

Detection of Fake Tweets Using Sentiment Analysis

Social platform is one of the most commonly used sites in the today’s world, and people from different places exchange information, express opinions, etc. Twitter is one of the most convenient platforms where Twitter data are frequently used for research and are one of the largest micro-blogging platforms. As there is an increase in number of spam accounts, there is a need to distinguish between genuine and fake user accounts. In Twitter, there is rise in the number of spam accounts, to spread malicious information among the users. So, to overcome the problem of spam in Twitter, an analysis of the opinions and the emotions of users in the form of tweets have been carried out. In this paper, we present a model which performs sentimental analysis on real-time data that are collected on a particular topic of interest for the users who recently posted on that topic. Using this model, we compute the sentiment score of each user with the content-based features to detect spam in Twitter. The proposed method makes use of a custom rule-based algorithm for detection of bots and compares it with few other algorithms like MLP, decision tree and random forest to see how efficient the model is in detection of spam accounts.

Non-Conventional Factors for Keystroke Dynamics as a Support Factor for Authenticating User

Keystroke Dynamics Are Most Frequently UsedIn Situation Where Password Security Is The Major Concern. In The Event That The User’s Secret Word Is Disclosed, AndThe Keystroke Rhythm Of The Genuine Client Is Known, The Application Will Not Accept The Fake User In Spite Of Having Valid Credentials. This Paper Focuses On Strengthening The Keystroke Dynamics By Introducing Non-Conventional Features For Authenticating A User Using Static Keystroke Dynamics. The Paper Also Discusses The Improvement In Far, Frr, Err, And Accuracy After The Application Of The Proposed Non-Conventional Feature Set Along With The Existing Timing Feature Set.

TINDAK PIDANA PENGGUNA IJAZAH PALSU STUDI KASUS PENGADILAN NEGERI KUPANG NOMOR 355//PID.SUS.2015//PN.KPG.

Fake diploma which is a criminal act which is regulated in article 263 of the Criminal Code, and specifically regulated in article 68 of Law No. 20 of 2003 concerning the National Education System and article 93 of Law No. 12 of 2012 concerning Higher Education, for that person to obtain the diploma must go through the educational process in accordance with the applicable rules so that the diploma used can be used properly and it is recognized that someone has passed a certain education, in the case of using fake diplomas there are several legal rules governing the use of diplomas and degrees, generally article 263 of the Criminal Code and specifically regulated in article 68 of Law No. 20 of 2003 concerning the National Education System and article 93 of Law No.12 of 2012 concerning Higher Education, in this case the judge decides to use article 68 Paragraph 2 against the perpetrator using a diploma and a fake Doctorate degree on case No.355 / PID.SUS / 2015 / PN.KPG. where in the concept of criminal law we recognize the principle of the Lex superior derogate legi afriori principle of legal interpretation which states that higher law excludes lower law.
 This study uses a method of normative legal research or literature study where the type of approach taken is the type of legislative approach (the statuta aproach) approach to legal argumentation (legal reasoning) and the approach of analyzing legal concepts and court decisions, with argumentation and systematization techniques, to knowing ; whether the legal sanctions that can be used by judges in making decisions against perpetrators of fake diploma users and how is the criminal responsibility against the use of fake diplomas, whether the verdicts of the Kupang District Court judges are appropriate to give a redundant effect on the perpetrators.
 It is hoped that in the case of the crime of forgery of the diploma the author expects law enforcement from the police to be more careful of the process of assigning suspects based on evidence and prosecutors in making indictments to be more careful in applying the articles before delegation to the Panel of Judges so that judges in receiving, examining and adjudicate cases more thoroughly against the facts revealed in the trial and pay more attention to the legal basis that will be applied to the perpetrator, in deciding the case so that it does not become a norm conflict in its application.
 Key words: Crime, Fake Diploma

Data poisoning attacks on neighborhood‐based recommender systems

AbstractNowadays, collaborative filtering recommender systems have been widely deployed in many commercial companies to make profit. Neighborhood‐based collaborative filtering (CF) is common and effective. To date, despite its effectiveness, there has been little effort to explore their robustness and the impact of data poisoning attacks on their performance. Can the neighborhood‐based recommender systems be easily fooled? To this end, we shed light on the robustness of neighborhood‐based recommender systems and propose a novel data poisoning attack framework, encoding the purpose of attack and constraint against them. We first illustrate how to calculate the optimal data poisoning attack, namely, UNAttack. We inject a few well‐designed fake users into the recommender systems such that target items will be recommended to as many normal users as possible. Extensive experiments are conducted on three real‐world datasets to validate the effectiveness and the transferability of our proposed method. In addition, some interesting phenomena can be found. For example, (i) neighborhood‐based recommender systems with Euclidean distance‐based similarity have strong robustness and (ii) the fake users can be transferred to attack the state‐of‐the‐art CF recommender systems such as neural CF and Bayesian personalized ranking matrix factorization.

Learning Product Rankings Robust to Fake Users

In many online platforms, customers' decisions are substantially influenced by product rankings as most customers only examine a few top-ranked products. Concurrently, such platforms also use the same data corresponding to customers' actions to learn how these products must be ranked or ordered. These interactions in the underlying learning process, however, may incentivize sellers to artificially inflate their position by employing fake users, as exemplified by the emergence of click farms. Motivated by such fraudulent behavior, we study the ranking problem of a platform that faces a mixture of real and fake users who are indistinguishable from one another. We first show that existing learning algorithms---that are optimal in the absence of fake users---may converge to highly sub-optimal rankings under manipulation by fake users. To overcome this deficiency, we develop efficient learning algorithms under two informational environments: in the first setting, the platform is aware of the number of fake users, and in the second setting, it is agnostic to the number of fake users. For both these environments, we prove that our algorithms converge to the optimal ranking, while being robust to the aforementioned fraudulent behavior; we also present worst-case performance guarantees for our methods, and show that they significantly outperform existing algorithms. At a high level, our work employs several novel approaches to guarantee robustness such as: (i) constructing product-ordering graphs that encode the pairwise relationships between products inferred from the customers' actions; and (ii) implementing multiple levels of learning with a judicious amount of bi-directional cross-learning between levels. Overall, our results indicate that online platforms can effectively combat fraudulent users without incurring large costs by designing new learning algorithms that guarantee efficient convergence even when the platform is completely oblivious to the number and identity of the fake users.

Defining the Types of «Fakers» in Social Media

Nowadays, internet users spend much of their time on social networks, where they share and generate content, support the causes and activities they like, get in touch with their peers, and generate audio-visual content. Besides, they also share their opinions with other users, thus producing User-Generated Content (UGC). The authors noted that UGC lacks proven scientific, professional, or academic quality. However, when content is generated massively in social networks, it can get viral and achieve the most significant engagement of users in the community. Furthermore, there is evidence that the content with the most significant impact on other users is the one that achieves the greatest engagement and support. The scientific review analysis indicated that usually, the content that achieves more impact and engagement in social media is related to fake news or published by fake users. In this context, the present study aims to theorize and define the concept of «faker» based on a review of previous studies. Main results show that a «faker» is a user who is not a real person, but pretends to be such. Based on the results of the exploratory analysis, the following 6 types of users classified as fakers were identified and analyzed: conspiranoid (users who share compulsive and self-taught content in which they share minimal details of the theory they support, have powerful firm beliefs, and always find a way to verify their hypotheses); proselytizing (users who try to gain followers by any means and convince other followers to follow them); narcissists (users who base their content on love and attraction to themselves and generate false content that reflects their own image as the main message); creators of chaos (users whose main objective is to generate chaos in social networks and base their arguments and theories on personal, professional, or political relationships among other users to generate conflicts that will increase the chaos within a closed community); satyr humor (users who generate content focused on the satire targeting public, mythological, ideological, or other characters or entities and defame others by focusing on the actions of public characters); paranoid tyrants (users who focus on the analysis of the information overload, which makes it difficult to interpret the contents on the Internet today). In the frame of this paper, the authors provided a discussion of important theoretical and practical implications of obtained results for the marketing industry and digital marketing in social media. Keywords: faker, fake content, social media, social network, UGC.

Driving license detection using QR code

We have proposed a system in which it simplifies the work of traffic police in detecting the fake driving license users. RTO Employee can login into this system and generate a new driving license with QR code for every applicant who has undergone test drive and who has successfully secured their learning license. In this system every employee can login with their credentials, they can generate a QR code and they can enter the details of applicant and generate new license with QR code attached to it. Traffic police can scan this QR code through Scanner app from mobile phone to retrieve the data present in QR code, if data retrieved in scanner app and data on the license mismatches then police can conclude that user is a fake user. QR code on the driving license contains name, father’s name, date of birth, house no., address and date up to when the card is valid.

Facebook Profile Credibility Detection using Machine and Deep Learning Techniques based on User’s Sentiment Response on Status Message

Recently, the impact of online Social Networks sites (SNS) has dramatically changed, and fake accounts became a vital issue that has rapidly evolved. This issue gives rise to how to assess and measure the credibility of User-Generated Content (UGC). This content is used in finding trusted sources of information on SNS like Facebook, Twitter, etc. Consequently, classifying users’ profiles and analyzing each user’s behavior response based on the content generated became a challenge that must be solved. One of the most significant approaches is Sentiment Analysis (SA) which plays a major role in assessing and detecting the credibility degree of each user account behavior. In this paper, the aim of the study is to measure and predict the user’s profile credibility by declaring the correlation degree among the UGC features that affect users’ responses to status messages. The proposed models were implemented using six Supervised Machine Learning classifiers, an Unsupervised Machine Learning cluster model, and a Deep Learning Neural Network (NN) model. The research paper presents two experiments to evaluate Facebook profile credibility. At first, we applied a binary classification model to classify profiles into fake or genuine users. Then, we conducted a classification model on genuine users based on the credibility theory by using the Analytical Hierarchical Process (AHP) approach and computed the credibility score for each. Secondly, we selected and analyzed a public Facebook page (CNN public page) and obtained data from it for users’ sentiment reactions and responses on statuses Messages relating to different topics on the period (2016/2017). Then, we performed LDA on the status corpus (Topic Modeling algorithm, Latent Dirichlet Allocation) to generate topic vectors. In addition, we performed Principal Component Analysis (PCA) method to visualize and classify each status topic distribution. Afterthought, we produced a status corpus cluster to classify users’ behaviors through statuses posted and users’ comments. As a conclusion of this study, the first experimental results achieved 95% and 99% accuracy to classify fake/genuine users and incredible/credible accounts, respectively. The second experiment outcome identified the clusters for the status corpus in 10 topic-features distribution and classified users’ contents into credible or not according to the final calculated credibility score.

A Contrast Metric for Fraud Detection in Rich Graphs

How can we detect fraud in a big graph with rich properties, as online fraudsters invest more resources, including purchasing large pools of fake user accounts and dedicated IPs, to hide their fraudulent attacks? To achieve robustness, existing approaches detected dense sub-graphs as suspicious patterns in an unsupervised way, such as average degree maximization. However, such approaches suffer from the bias of including more nodes than necessary, resulting in lower accuracy and increased need for manual verification. Therefore, we propose HoloScope, which introduces a novel metric “contrast suspiciousness” integrating information from graph topology and spikes to more accurately detect fraudulent users and objects. Contrast suspiciousness dynamically emphasizes the contrasting patterns between fraudsters and normal users, making HoloScope capable of distinguishing the synchronized and strange behaviors of fraudsters by means of topology, bursts and drops, and rating scores. In addition, we provide theoretical bounds for how much this method increases the time cost needed for fraudsters to conduct adversarial attacks. Moreover, HoloScope has a concise framework and sub-quadratic time complexity, making the algorithm reproducible and scalable. In extensive experiments, HoloScope achieved significant accuracy improvements on real data with injected labels and true labels, when compared with state-of-the-art fraud detection methods.

Fake Profile Identification in Online Social Networks

There is a tremendous increase in technologies these days.. Mobiles are becoming smart. Technology is associated with online social networks which has become a part in every one’s life in making new friends and keeping friends , their interests are known easier. But this increase in networking online make many problems like faking their profiles, online impersonation having become more and more in present days. Users are fed with more unnecessary knowledge during surfing which are posted by fake users. Researches have observed that 20% to 40% profiles in online social networks like facebook are fake profiles. Thus this detection of fake profiles in online social networks results into solution using frameworks.

Identification of Fake Accounts for Making Trust on Network using Machine Learning

Social Networks are gradually influencing the people to communicate with each other and share the personal, public related information. Different social networks have different target people. In particular Facebook used to establish the friendship, LinkedIn to find new Job, these Rabid growth of social networks, people tend to misuse the social networks to spoil others reputation or to steal the others information’s. Fake profiles are dangerous in social networks platform. It is essential to identify the fake users from social networks. This work presents the novel approach to predict and differentiate the fake user and legitimate user from social networks by using Machine Learning algorithm and we achieved significant results.

An enhanced graph-based semi-supervised learning algorithm to detect fake users on Twitter

Over the the past decade, social networking services (SNS) have proliferated on the web. The nature of such sites makes identity deception easy, providing a fast means for creating and managing identities, and then connecting with and deceiving others. Fake users are those accounts specifically created for purposes such as stalking or abuse of another user, for slander, or for marketing. The current system for detecting deception depends on behavioral, non-behavioral and user-generated content (UGC) information gathered from users. Although these methods have high detection accuracy, they cannot be implemented in databases with massive volumes of data. To address this issue, this paper proposes an enhanced graph-based semi-supervised learning algorithm (EGSLA) to detect fake users from a large volume of Twitter data. The proposed method encompasses four modules: data collection, feature extraction, classification and decision making. Data collected from Twitter using Scrapy is utilized for the evaluation. The performance of the proposed algorithm is tested with existing game theory, k-nearest neighbor (KNN), support vector machine (SVM) and decision tree techniques. The results show that the proposed EGSLA algorithm achieves 90.3% accuracy in spotting fake users.

A survey on detecting spam accounts on Twitter network

Social networks have become an inseparable part of our lives today. Services such as Facebook, Twitter, Instagram, Google + and LinkedIn in particular have had a significant place in Internet use in recent years. People establish instant interactions between each other over the Internet using these social services. They get many advantages such as creating their own groups, being informed about different interest areas and being able to make many contacts. Twitter is one of the mostly used platforms among the social networks. A social network that is being used so commonly has become a target for the vicious people (spammers). There is an increase in the number of spammers on Twitter too. Malicious content and messages (spams) prepared by the spammers do threat the security as well as performance. The first and most important condition to protect against this threat is to know the harmful methods of spam. Thus, this will make it easier to detect and protect. In this study, prominent detection methods of spams are analyzed. How the real users and fake users are distinguished as well as weak and strong aspects of the methods for these processes are compared and evaluated.

Robust active attacks on social graphs

In order to prevent the disclosure of privacy-sensitive data, such as names and relations between users, social network graphs have to be anonymised before publication. Naive anonymisation of social network graphs often consists in deleting all identifying information of the users, while maintaining the original graph structure. Various types of attacks on naively anonymised graphs have been developed. Active attacks form a special type of such privacy attacks, in which the adversary enrols a number of fake users, often called sybils, to the social network, allowing the adversary to create unique structural patterns later used to re-identify the sybil nodes and other users after anonymisation. Several studies have shown that adding a small amount of noise to the published graph already suffices to mitigate such active attacks. Consequently, active attacks have been dubbed a negligible threat to privacy-preserving social graph publication. In this paper, we argue that these studies unveil shortcomings of specific attacks, rather than inherent problems of active attacks as a general strategy. In order to support this claim, we develop the notion of a robust active attack, which is an active attack that is resilient to small perturbations of the social network graph. We formulate the design of robust active attacks as an optimisation problem and we give definitions of robustness for different stages of the active attack strategy. Moreover, we introduce various heuristics to achieve these notions of robustness and experimentally show that the new robust attacks are considerably more resilient than the original ones, while remaining at the same level of feasibility.

From similarity perspective: a robust collaborative filtering approach for service recommendations

Collaborative filtering (CF) is a technique commonly used for personalized recommendation and Web service quality-of-service (QoS) prediction. However, CF is vulnerable to shilling attackers who inject fake user profiles into the system. In this paper, we first present the shilling attack problem on CF-based QoS recommender systems for Web services. Then, a robust CF recommendation approach is proposed from a user similarity perspective to enhance the resistance of the recommender systems to the shilling attack. In the approach, the generally used similarity measures are analyzed, and the DegSim (the degree of similarities with top k neighbors) with those measures is selected for grouping and weighting the users. Then, the weights are used to calculate the service similarities/differences and predictions.We analyzed and evaluated our algorithms using WS-DREAM and Movielens datasets. The experimental results demonstrate that shilling attacks influence the prediction of QoS values, and our proposed features and algorithms achieve a higher degree of robustness against shilling attacks than the typical CF algorithms.

Spammer Detection and Fake User Identification on Social Networks

Social networking sites engage millions of users around the world. The users' interactions with these social sites, such as Twitter and Facebook have a tremendous impact and occasionally undesirable repercussions for daily life. The prominent social networking sites have turned into a target platform for the spammers to disperse a huge amount of irrelevant and deleterious information. Twitter, for example, has become one of the most extravagantly used platforms of all times and therefore allows an unreasonable amount of spam. Fake users send undesired tweets to users to promote services or websites that not only affect legitimate users but also disrupt resource consumption. Moreover, the possibility of expanding invalid information to users through fake identities has increased that results in the unrolling of harmful content. Recently, the detection of spammers and identification of fake users on Twitter has become a common area of research in contemporary online social Networks (OSNs). In this paper, we perform a review of techniques used for detecting spammers on Twitter. Moreover, a taxonomy of the Twitter spam detection approaches is presented that classifies the techniques based on their ability to detect: (i) fake content, (ii) spam based on URL, (iii) spam in trending topics, and (iv) fake users. The presented techniques are also compared based on various features, such as user features, content features, graph features, structure features, and time features. We are hopeful that the presented study will be a useful resource for researchers to find the highlights of recent developments in Twitter spam detection on a single platform.

Fake (Sybil) Account Detection Using Machine Learning

Over the past few years, social networks have seen tremendous growth in users. There are 2.32 billion monthly active users (MAU) on the Facebook social network as of December 31, 2018. As compared to 2.32 billion monthly active users (MAUs) for 4th quarter 2018 (Source: Facebook 1/30/19), and it has been increase with an approx. rate of 9% each year. Almost 10 million likes and share buttons are clicked on various websites daily (Source: Facebook as of 10/2/2014). About 293,000 statuses are updated, 136,000 photos are uploaded and 510,000 comments are posted every minute. (Source: The Social Skinny). Overall, it is estimated that around 3 to 4% of the active Facebook accounts on the site are still fake. These fake accounts are called Sybil accounts, they may be human or bots operated with an ulterior motive. These Sybil accounts try to influence users views or befriend other users to gain those user’s information for ill intents. In this paper, we focus on detecting fake user on the Facebook social network. The overall contribution in this article are creation of a dataset for fake user detection and comparative analysis of different model over it.

Trust Model Based On Islamic Business Ethics and Social Network Analysis

Buyers and sellers in e-commerce market such as e-auction form a virtual community. They use the feedback system to rate each other following a completed transaction and these ratings are used to build their reputation in the virtual community. Existing reputation systems can often be easily manipulated by forming cohesive group in giving fake user feedbacks to increase their respective reputation. This practice is a clear violation of Islamic business ethics. In addition, there is currently no real-time support for reputation system and this causes users to be misinformed on the reputation of a seller. To improve the reputation system this study developed a trust framework based on business Islamic ethics. In this paper, a trust model which evaluates conformance to nine Islamic business ethical codes is proposed to calculate users’ initial trust value based on their ethical behavior. The trust model proposed the Islamic business ethics algorithm which calculates the user compliance to Islamic business ethics (IBE) score based on trading partner’s feedbacks. Because of feedback frauds can still occur, this study introduces a cohesive group algorithm to track users who collaborate to give false feedbacks. The cohesive group algorithm applied k-core algorithms which is capable of determining the strength of the relationship of every user in the cohesive group. The cohesive group algorithm also proposed a cohesive score to determine the feedback reliability of every user’s transaction based on the user’s k-core and the highest k-core. In the group user reputation (trust score) is measured by considering the feedback reliability status for all transactions. A reputation prototype system for e-auction was developed as the test bed to validate the trust model through simulation of the set of initial experiments, showing the feasibility and benefit of the model.

A robust recommended system based on attack detection

SummaryIn the increasingly fierce competition in e‐commerce sites, the recommendation system has brought great benefits to the site, but some unscrupulous businesses use the recommended system algorithm loopholes, the use of bulk injection of some fake users, and the ratings of these users with the normal user's rating. Therefore, when calculating user similarity, it is easy to enter the user's neighborhood circle, because the false user takes a high score (“push attack”) or a low score (“null attack”) on the target project. The recommendation scores will be biased, and it is important to detect these false users for the recommendation system and maintain a good e‐commerce competitive environment. In this paper, we propose a recommendation algorithm that divides user‐generated ratings into normal ratings and non‐generic ratings and refine and use state information to minimize the impact of spurious malicious users. Our algorithm first ensures that the recommender system is stable against the three main attack modes (random attack, average attack, power flow attack). Through the analysis of the real data, we verify the performance of the proposed scheme and compare our algorithm with the existing one.

An Era of AI-personation & Self(ie) Surveillance

Any discussion of the social invisibilities engendered by the Internet necessarily demands further questioning as to how visibility, as an increasing cultural norm, has produced new inequalities in real life. This contribution combines autoethnographic research, social media analysis, and data analytics with theoretical frameworks such as phenomenology and psychology to globally investigate our current culture of AI-catfishing, social media metrics, and metrics manipulation. 
 My paper raises questions about re-materializing digital divides and inequalities in the “offline world” through citing self-surveillance techniques and algorithmic biases to show how we are both at the whim of these AI-inflected prejudices but also complicit in reproducing them, whether through government coercion or our own cultural norms and rules. I trace our relationship with music technology to outline a trajectory of sensory disconnect and co-produced community — a framework for understanding current cultural phenomena and the ethics of distributed data, privacy, and the rendering of our bodies as a new kind of transaction, and currency. The rise of fake news is re-contextualized within the widespread rise of fake users: the various impersonations of self even and especially through AI.