Design and Evaluation of a Real-Time URL Spam Filtering Service

Abstract

On the heels of the widespread adoption of web services such as social networks and URL shorteners, scams, phishing, and malware have become regular threats. Despite extensive research, email-based spam filtering techniques generally fall short for protecting other web services. To better address this need, we present Monarch, a real-time system that crawls URLs as they are submitted to web services and determines whether the URLs direct to spam. We evaluate the viability of Monarch and the fundamental challenges that arise due to the diversity of web service spam. We show that Monarch can provide accurate, real-time protection, but that the underlying characteristics of spam do not generalize across web services. In particular, we find that spam targeting email qualitatively differs in significant ways from spam campaigns targeting Twitter. We explore the distinctions between email and Twitter spam, including the abuse of public web hosting and redirector services. Finally, we demonstrate Monarch's scalability, showing our system could protect a service such as Twitterwhich needs to process 15 million URLs/day-for a bit under $800/day.

CS-1-SVM: Improved One-class SVM for Detecting API Abuse on Open Network Service

“…In details, Most of those text based detection [6][7][8][9][10] methods just focused on text analyze but ignored the user's behaviors, and then induced the high FNR (false negative rate) and low TPR. Likewise most behavior model based Fig.…”

“…The optimum value for the parameter was determined by cross validation. (9) Another important comparison among content analysis method like those proposed by reference [6][7][8][9][10], COMPA [11] and the proposed CS-1-SVM shows different application efficiency.…”

“…Earlier studies focus on analysis of static information (e.g. text, URL and IP) *Address correspondence to this author at the College of Network Communication, Zhejiang Yuexiu University of Foreign Languages, Shaoxin, China; Tel: +8615957572387; E-mail: chenht80@163.com like traditional detection on E-mail spam [3,[6][7][8][9][10], which can be easily implemented by the mature technology on E-mail spam detection. But nowadays, tools and techniques used by attackers are more complicated.…”

A Taxonomy of Attacks and a Survey of Defence Mechanisms for Semantic Social Engineering Attacks

“…The work represents research with a product outcome that is usable to the internet community against a known vulnerability of a popular social media platform. Other URL detection mechanisms have been demonstrated by Thomas et al [2011], the study introduces a system that provides real-time URL spam filtering. The system proposed, Monarch, performs realtime filtering of scam, phishing and malware URLs that are submitted to web services through the use of linear classification with the combination of iterative parameter mixing and subgradient L1-regularisation; calculating an overall accuracy of 91% and 0.87% false positive margin.…”

An Intellect Learning on E-Mail Security and Fraud, Spam and Phishing

“…This will stretchconceptions and persuades to do advanceexploration. Kurt Thomas, Chris Grier et al [37] industrialized Monarch a real-time system for filtering scam, phishing, and malware URLs as they are acquiesced to web amenities. Monarch's architecture simplifies too many web amenities being embattled by URL spam, precise classification fulcrums on having a cherishedindulgent of the spam crusadesmolesting anamenity.…”