Click Fraud Detection with Bot Signatures

A user click fraud detection method based on Top-Rank-k frequent pattern mining algorithm is presented to solve the click fraud problem appearing in current online advertising. Firstly, this method combines the click frequency of event samples, calculates the real evaluation score of click stream, and the click stream density function and evaluation score expression under multi-dimensional variables, and further obtains the time complexity of the next user’s click fraud process. Secondly, according to the Top-Rank-k frequent pattern, the process of click fraud detection algorithm is designed, and the click fraud user is analyzed and obtained. The results show that this method has good efficiency and correctness, and is superior to other similar algorithms.

show abstract

“…Step 8: Depth calculation is conducted, and arrival rate is calculated as per Eqs. (5) and (6) by the use of output values.…”

Section: User Click Fraud Detection Methodsmentioning

confidence: 99%

User click fraud detection method based on Top-Rank-k frequent pattern mining

Pan

Wang

2019

Int. J. Mod. Phys. B

View full text Add to dashboard Cite

show abstract

“…We started up a Click Fraud Investigation team, and enlisted their help to comb through weblogs and identify click fraud attacks, and then provide those as labeled cases for our system which we called "Clickfraud Bot Signatures" [28]. This was a "classic" machine learning approach in which a set of labeled cases are used to train the system to recognize attacks.…”

Section: Meanwhile Click Fraud Enters An Infinite Loopmentioning

confidence: 99%

The Making of a Large-Scale Online Ad Server: Practical Lessons Building One of the World's Largest Online Ad Servers

Kitts

2013

2013 IEEE 13th International Conference on Data Mining Workshops

Self Cite

View full text Add to dashboard Cite

Data Mining promises potential improvements in a variety of real-world problems. However large-scale implementations face an array of challenges between their inception and deployment, many of which are not technical in nature. This paper will describe the author's experience building one of the largest data mining systems in the world. The objective is to help orientate practitioners to the challenges involved in system implementation, and to suggest general strategies that practitioners can use to successfully navigate development.

show abstract

“…Passive detection approaches, on the other hand, apply data analysis/mining techniques to recognize the behaviour pattern of traffics (e.g. [11,19,21,23,25,27]). While active detection techniques typically adopt the signature based detection mechanism to mark the fraudulent traffic, passive detection techniques can use both signature based (e.g.…”

mentioning

confidence: 99%

“…While active detection techniques typically adopt the signature based detection mechanism to mark the fraudulent traffic, passive detection techniques can use both signature based (e.g. [11]) and anomaly based (e.g. [23]) approaches to identify frauds.…”

mentioning

confidence: 99%

Detecting coalition attacks in online advertising: A hybrid data mining approach

Zhang¹,

Feng²

2016

BDIA

View full text Add to dashboard Cite

Coalition attack is nowadays one of the most common type of attacks in the industry of online advertising. In this paper, we attempt to mitigate the problem of frauds by proposing a hybrid framework that detects the coalition attacks based on multiple metrics. We also articulate the theoretical basis for these metrics to be integrated into the hybrid framework. Furthermore, we instance the framework with two metrics and develop a detection system that identifies the coalition attacks from two distinguish perspectives.

show abstract

Click Fraud Detection with Bot Signatures

Cited by 10 publications

References 4 publications

User click fraud detection method based on Top-Rank-k frequent pattern mining

User click fraud detection method based on Top-Rank-k frequent pattern mining

The Making of a Large-Scale Online Ad Server: Practical Lessons Building One of the World's Largest Online Ad Servers

Detecting coalition attacks in online advertising: A hybrid data mining approach

Contact Info

Product

Resources

About