Quasi-cliques Analysis for IRC Channel Thread Detection

Jocelyn Bernard, Sicong Shao, Cihan Tunc, Hamamache Kheddouci, Salim Hariri

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations


Internet Relay-Chat (IRC) is a real-time communication protocol that allows broadcasting and direct messages in the form of text. Hence, IRC has been widely used especially by hacker communities to communicate and plan malicious activities. Even though widely used for malicious intent, little research has been done on the analysis of the social network among hacker communities in IRC. Hence, it is crucial to analyze IRC communities and their connection. In this paper, we classified IRC messages based on their intent and created their communication graphs to compute metadata on the relation between hackers. For this purpose, we apply autonomic computing for IRC monitoring and data collection, perform deep learning to classify IRC messages into different threat levels, and then apply the quasi-clique model to analyze hacker social networks, and identify the hidden relations between them.

Original languageEnglish (US)
Title of host publicationComplex Networks and Their Applications VII - Volume 1 Proceedings The 7th International Conference on Complex Networks and their Applications COMPLEX NETWORKS 2018
EditorsRenaud Lambiotte, Luis M. Rocha, Pietro Lió, Hocine Cherifi, Luca Maria Aiello, Chantal Cherifi
Number of pages12
ISBN (Print)9783030054106
StatePublished - 2019
Event7th International Conference on Complex Networks and their Applications, COMPLEX NETWORKS 2018 - Cambridge, United Kingdom
Duration: Dec 11 2018Dec 13 2018

Publication series

NameStudies in Computational Intelligence
ISSN (Print)1860-949X


Other7th International Conference on Complex Networks and their Applications, COMPLEX NETWORKS 2018
Country/TerritoryUnited Kingdom

ASJC Scopus subject areas

  • Artificial Intelligence


Dive into the research topics of 'Quasi-cliques Analysis for IRC Channel Thread Detection'. Together they form a unique fingerprint.

Cite this