ORFEL: Efficient detection of defamation or illegitimate promotion in online recommendation

Gimenes, Gabriel P.; Cordeiro, Robson L. F.; Rodrigues-Jr, José F.

doi:10.1016/j.ins.2016.09.006

Cited by 12 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Auter and Fine [29] found that attack advertising on social media sometimes can act as an important measure used by a politician to compete with his opponent on an election campaign. Gimenes et al [30] found that the low-valued user-product recommendation in some mobile apps can lead to the security problems of illegitimate promotion, and proposed the method of using vertex-centric asynchronous parallel processing of bipartite graphs to detect illegitimate promotion. Zhang [31] proposed the deep learning algorithms based on lexical features which can be used for classifying and visualizing the advertisements to detect the malicious advertisements.…”

Section: Related Workmentioning

confidence: 99%

Social Media Users Send Promotional Links to Strangers: Legitimate Promotion or Security Vulnerability?

Yue

Liu

2020

IEEE Access

View full text Add to dashboard Cite

Nowadays, many users make money by publishing content on social media platforms. In order to attract users' attention, they often take measures to promote themselves. The security vulnerabilities in social media platforms may provide convenience for their user promotion work. We call this type of vulnerability the user promotion security vulnerability (UPSV). UPSV may cause unfair competition and endanger the interests of legitimate users and the social media platforms. Therefore it has great research significance to find and fix this vulnerability. In this paper, we propose a UPSV which widely exists in the function of sending messages to strangers of in-app chatting of many social media platforms. We first analyzed this vulnerability in some apps, and then YY app (China's largest live streaming platform) was chosen as the research object to verify the actual effect of the vulnerability on illegitimate user promotion. We took the method of promoting a target YY streamer through sending promotional links to viewers, and to improve promotion effect, we used the method of user preference learning to select viewers for promotion. The experimental results show that among the promoted viewers, more than 44% entered the target streamers' channels to watch live streaming, more than 21% followed the target steamers, and more than 13% gave gifts to the target steamers. It fully proves that this UPSV is real, exploitable and harmful, and we also proposed some fix suggestions to help the platforms to fix it. INDEX TERMS Social media, user promotion, security vulnerability, in-app chatting, preference learning. I. INTRODUCTION

show abstract

Section: Related Workmentioning

confidence: 99%

Social Media Users Send Promotional Links to Strangers: Legitimate Promotion or Security Vulnerability?

Yue

Liu

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…O trabalho Online-Recommendation Fraud Excluder (ORFEL) 2 (Gimenes et al, 2016) foi desenvolvido para tratar o problema de detecção de fraudes em redes de recomendação. Nestas redes,é possível criar usuários falsos para difamar ou promover produtos por meio de recomendações eletrônicas ilegítimas ao longo do tempo, o que dificulta sobremaneira o problema.…”

Section: Identificação De Fraudesunclassified

Contribuições em técnicas analíticas sobre dados representáveis como grafos: delineamento e identificação de padrões para o suporte à decisão.

Junior¹,

Fernando²

View full text Add to dashboard Cite

The text presents a systematized view of the research and work performed by the author in the field of Databases, with focus on data representable as graphs. This theme is divided in three parts: algorithms for large-scale graph processing, which concerns techniques on vertex-centric asynchronous parallel processing for improved performance over one single processing node; analytical processing of graphs for the detection of patterns, which includes statistical, topologic, algorithmic, and algebraic techniques applied over properties extracted from graphs, with broad experimentation over the database of the Digital Bibliography & Library Project; and, in the third part, visualization based on the graph model, in which graphs are the goal, or the method, to obtain graphical representations of the data. This work also touches on the theme of Content-based Data Management, a field in which the candidate works significantly; the document describes methodologies that use concepts of Content-based Data Retrieval for information retrieval, visualization, classification, and analysis. The text delineates the fundamentals and assumptions with which the research lines have been exploited by the author, with emphasis on the works and contributions of the last six years of academic work, the period after the end of the Doctorial term.

show abstract

“…Experiments of scalability over the number of seeds.Source:Gimenes, Cordeiro and Rodrigues-Jr (2016).…”

mentioning

confidence: 99%

Data analysis over large-scale graphs using vertex-centric asynchronous parallel processing

Gimenes¹

View full text Add to dashboard Cite

show abstract

ORFEL: Efficient detection of defamation or illegitimate promotion in online recommendation

Cited by 12 publications

References 35 publications

Social Media Users Send Promotional Links to Strangers: Legitimate Promotion or Security Vulnerability?

Social Media Users Send Promotional Links to Strangers: Legitimate Promotion or Security Vulnerability?

Contribuições em técnicas analíticas sobre dados representáveis como grafos: delineamento e identificação de padrões para o suporte à decisão.

Data analysis over large-scale graphs using vertex-centric asynchronous parallel processing

Contact Info

Product

Resources

About