AN ALGORITHM FOR MONITORING PRIVILEGED SESSIONS AND DETECTING RISKY ACTIONS IN INFORMATION SYSTEMS BASED ON CONTEXTUAL AND BEHAVIORAL ANALYSIS

Monitoring privileged user activity in information systems plays a vital role in protecting critical information resources. Conventional access control mechanisms verify granted permissions but cannot always detect their misuse. Effective privileged-session monitoring therefore requires joint assessment of habitual user behavior, sequences of performed actions, and associated risk levels. This paper proposes an integrated algorithmic model combining user profiling through K-Prototypes clustering, session anomaly detection using One-Class Support Vector Machines (OC-SVM), and contextual risk scoring. The mathematical formulation, operational steps, and experimental evaluation methodology of the proposed model are presented. The approach is designed to account for the relationships between contextual features and user actions within privileged sessions.

Authors

Publication Details

Journal
International journal of technology and academic research
Published
2026-11-18
Primary Topic
Network Security and Intrusion Detection
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

AN ALGORITHM FOR MONITORING PRIVILEGED SESSIONS AND DETECTING RISKY ACTIONS IN INFORMATION SYSTEMS BASED ON CONTEXTUAL AND BEHAVIORAL ANALYSIS

Kengesbaev Salauat Kuanishbayevich
International journal of technology and academic research
Network Security and Intrusion Detection
article

AN ALGORITHM FOR MONITORING PRIVILEGED SESSIONS AND DETECTING RISKY ACTIONS IN INFORMATION SYSTEMS BASED ON CONTEXTUAL AND BEHAVIORAL ANALYSIS

Kengesbaev Salauat Kuanishbayevich
article en

Abstract

Monitoring privileged user activity in information systems plays a vital role in protecting critical information resources. Conventional access control mechanisms verify granted permissions but cannot always detect their misuse. Effective privileged-session monitoring therefore requires joint assessment of habitual user behavior, sequences of performed actions, and associated risk levels. This paper proposes an integrated algorithmic model combining user profiling through K-Prototypes clustering, session anomaly detection using One-Class Support Vector Machines (OC-SVM), and contextual risk scoring. The mathematical formulation, operational steps, and experimental evaluation methodology of the proposed model are presented. The approach is designed to account for the relationships between contextual features and user actions within privileged sessions.

International journal of technology and academic research
Network Security and Intrusion Detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon