Visible to the public Detection of Spammers in the Reconnaissance Phase by machine learning techniques

TitleDetection of Spammers in the Reconnaissance Phase by machine learning techniques
Publication TypeConference Paper
Year of Publication2018
AuthorsJeyasudha, J., Usha, G.
Conference Name2018 3rd International Conference on Inventive Computation Technologies (ICICT)
Date Publishednov
ISBN Number978-1-5386-4985-5
Keywordsartificial honeypot profiles, Classification algorithms, Conferences, DspamRPfast model, Feature Based Strategy, learning (artificial intelligence), machine learning, machine learning algorithms, machine learning techniques, Network reconnaissance, organizational social network, professional social networks, pubcrawl, reconnaissance phase, resilience, Resiliency, Scalability, security of data, Social Network Fake Profiles, social networking (online), supervised learning, Testing, Twitter, Xgboost

Reconnaissance phase is where attackers identify their targets and how to collect information from professional social networks which can be used to select and exploit targeted employees to penetrate in an organization. Here, a framework is proposed for the early detection of attackers in the reconnaissance phase, highlighting the common characteristic behavior among attackers in professional social networks. And to create artificial honeypot profiles within the organizational social network which can be used to detect a potential incoming threat. By analyzing the dataset of social Network profiles in combination of machine learning techniques, A DspamRPfast model is proposed for the creation of a classifier system to predict the probabilities of the profiles being fake or malicious and to filter them out using XGBoost and for the faster classification and greater accuracy of 84.8%.

Citation Keyjeyasudha_detection_2018