Paper published in a book (Scientific congresses, symposiums and conference proceedings)
KAVE: A Knowledge-Based Multi-Agent System for Web Vulnerability Detection
ROSA MESQUITA RAMIRES, Rafael Francisco; Respício, Ana; Medeiros, Ibéria
2024In Chang, Rong N. (Ed.) Proceedings - 2024 IEEE International Conference on Web Services, ICWS 2024
Peer reviewed
 

Files


Full Text
KAVE_A_Knowledge-Based_Multi-Agent_System_for_Web_Vulnerability_Detection.pdf
Author postprint (1.24 MB)
Download

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Multi-Agent System; Multi-Layer Knowledge Graph; Software Security; Static Analysis; Web Application Vulnerabilities; Knowledge based; Knowledge graphs; Multi-layer knowledge graph; Multi-layers; Multiagent systems (MASs); Software security; Vulnerability detection; WEB application; Web application vulnerability; Web applications; Artificial Intelligence; Computer Networks and Communications; Computer Science Applications; Information Systems; Information Systems and Management
Abstract :
[en] The growing use of the web has led to a rise in cyber attacks exploiting software vulnerabilities, thereby causing significant damage to companies and individuals. Static analysis tools can assist programmers in identifying vulnerabilities within their code. However, these tools are prone to producing false positives and lack precision, which relegates them to a somewhat marginalised role in software development. This paper proposes a new and more effective static analysis approach for assessing and evaluating web applications against vulnerabilities by using a knowledge-based multi-agent system web vulnerability detector called KAVE. The multi-agent system performs static taint analysis over a specially designed multi-layer knowledge graph, whereas this graph aggregates diverse interconnected representations of the lexical and semantic features of the application's source code, their data and control flows, and function calls. Additionally, this graph integrates security properties associated with vulnerabilities. The evaluation results of KAVE and comparison with existing tools showed that KAVE employs an effective and efficient method to detect vulnerabilities in web applications, finding 235 vulnerabilities with a precision of 95.9% over 12 open-source PHP web applications.
Research center :
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > SerVal - Security, Reasoning & Validation
Disciplines :
Computer science
Author, co-author :
ROSA MESQUITA RAMIRES, Rafael Francisco  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SerVal ; Universidade de Lisboa, Lasige, Di, Faculdade de Ciências, Portugal
Respício, Ana;  Universidade de Lisboa, Lasige, Di, Faculdade de Ciências, Portugal
Medeiros, Ibéria;  Universidade de Lisboa, Lasige, Di, Faculdade de Ciências, Portugal
External co-authors :
yes
Language :
English
Title :
KAVE: A Knowledge-Based Multi-Agent System for Web Vulnerability Detection
Publication date :
July 2024
Event name :
2024 IEEE International Conference on Web Services (ICWS)
Event place :
Shenzhen, Chn
Event date :
07-07-2024 => 13-07-2024
Main work title :
Proceedings - 2024 IEEE International Conference on Web Services, ICWS 2024
Editor :
Chang, Rong N.
Publisher :
Institute of Electrical and Electronics Engineers Inc.
ISBN/EAN :
9798350368550
Pages :
12
Peer reviewed :
Peer reviewed
Focus Area :
Computational Sciences
Funding text :
This work was supported by FCT through the LASIGE Research Unit, ref. UIDB/00408/2020 (https://doi.org/10.54499/UIDB/00408/2020) and ref. UIDP/00408/2020 (https://doi.org/10.54499/UIDP/00408/2020). It is based upon work from COST Action CA22104 - Behavioral Next Generation in Wireless Networks for Cyber Security (BEiNG-WISE), supported by COST (European Cooperation in Science and Technology) www.cost.eu.
Available on ORBilu :
since 06 February 2025

Statistics


Number of views
88 (11 by Unilu)
Number of downloads
77 (3 by Unilu)

Scopus citations®
 
1
Scopus citations®
without self-citations
0
OpenCitations
 
0
OpenAlex citations
 
2

Bibliography


Similar publications



Contact ORBilu