Investigative Behavior Profiling with One Class SVM for Computer Forensics

Bhukya, Wilson Naik; Banothu, Sateesh Kumar

doi:10.1007/978-3-642-25725-4_33

Cited by 5 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Customers of a PC are familiar with the archives on that system and where they are discovered [3]. Any journey for specific records is obligated to be centered around and compelled.…”

Section: User Behavior Profilingmentioning

confidence: 99%

User Behaviour Profiling in Cloud using One Class SVM: A Review

Paruchuri¹,

Kumar²,

Sridhar³

et al. 2016

IJSIA

View full text Add to dashboard Cite

Distributed computing guarantees to on a very basic level change the way we utilizePCs and get to and store our own specific and business data. With these new registering and correspondences models develop new data security challenges. Existing information security structures, for instance, encryption have fizzled in imagining information theft strikes, particularly those executed by an insider to the cloud supplier. We propose a substitute methodology for securing information in the cloud utilizing adversarial mimic improvement. We screen data access in the cloud and perceive unpredictable data access outlines. Right when unapproved access is suspected and after that confirmed using test questions, we dispatch a disinformation strike by giving back a considerable measure of fake information to the attacker. This secures against the misuse of the customer's real data. Trials coordinated in a neighbor-hood archive setting give confirmation this technique may give unprecedented levels of customer data security in a Cloud space.

show abstract

“…Customers of a PC are familiar with the archives on that system and where they are discovered [3]. Any journey for specific records is obligated to be centered around and compelled.…”

Section: User Behavior Profilingmentioning

confidence: 99%

User Behaviour Profiling in Cloud using One Class SVM: A Review

Paruchuri¹,

Kumar²,

Sridhar³

et al. 2016

IJSIA

View full text Add to dashboard Cite

show abstract

“…Research on criminal profiling in the area of cyber crime is limited. Bhukya and Banothu [3] have captured GUI-based user behavior to construct user profiles and have applied support vector machines to classify users. McKinney and Reeves [14] have proposed a model for developing user profiles by analyzing processes running on a computer and detecting masquerades.…”

Section: Related Workmentioning

confidence: 99%

Profiling and Tracking a Cyberlocker Link Sharer in a Public Web Forum

Fan

Chow

2015

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

The expanding utilization of cyberlocker services is driven by the illegal exchange of copyrighted materials. In fact, the illegal exchange of copyrighted materials is the largest contributor to global Internet traffic. However, due to the anonymity provided by cyberlockers, it is difficult to track user identities directly from cyberlocker sites. Since cyberlocker users upload and share links via third-party sites, it is possible to harvest cyberlocker-related data from these sites and connect the data to specific users. This chapter describes a framework for collecting cyberlocker data from web forums and using cyberlocker link sharing behavior to identify users. Multidimensional scaling analysis and agglomerative hierarchical clustering analysis are performed on user profiles to yield clusters of forum users with similar sharing characteristics. The experimental results demonstrate that the framework provides valuable insights in investigations of cyberlocker-based piracy.

show abstract

“…McKinney, et al [10] have proposed a masquerade detection method, which creates a user profile using a naive Bayesian classifier that analyzes running computer processes. Bhukya and Banothu [1] engage GUI-based behavior to construct user profiles; a support vector machine learning algorithm is used to train the system to classify users. To our knowledge, there is little, if any, research that has explicitly focused on identifying web users based on their browsing history.…”

Section: Related Workmentioning

confidence: 99%

Web User Profiling Based on Browsing Behavior Analysis

Fan

Chow

2014

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Part 1: Internet Crime InvestigationsInternational audienceDetermining the source of criminal activity requires a reliable means to estimate a criminal’s identity. One way to do this is to use web browsing history to build a profile of an anonymous user. Since an individual’s web use is unique, matching the web use profile to known samples provides a means to identify an unknown user. This paper describes a model for web user profiling and identification. Two aspects of browsing behavior are examined to construct a user profile, the user’s page view number and page view time for each domain. Four weighting models, based on the term frequency and term frequency – inverse document frequency weighting schemes, are proposed and compared. Experiments involving 51 personal computers demonstrate that the profiling model is very effective at identifying web users

show abstract

Investigative Behavior Profiling with One Class SVM for Computer Forensics

Cited by 5 publications

References 17 publications

User Behaviour Profiling in Cloud using One Class SVM: A Review

User Behaviour Profiling in Cloud using One Class SVM: A Review

Profiling and Tracking a Cyberlocker Link Sharer in a Public Web Forum

Web User Profiling Based on Browsing Behavior Analysis

Contact Info

Product

Resources

About