Advanced International Journal for Research

E-ISSN: 3048-7641   •   Impact Factor: 9.11

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Call for Paper Volume 7, Issue 6 (November-December 2026) Submit your research before last 3 days of December to publish your research paper in the issue of November-December.
Submit Research Paper Join as a Reviewer

Plagiarism is checked by the leading plagiarism checker TurnItIn

Call for Paper

Volume 7 Issue 6
November-December 2026

Submit your research paper

Indexing Partners
Academia Advanced Sciences Index Bielefeld Academic Search Engine CiteSeer DRJI Google Scholar Independent Search Engine & Directory Network ISI (International Scientific Indexing) Issuu Mendeley Research Networks
RefSeek ResearcherId - Thomson Reuters ResearchGate Scirus Scribd Semantic Scholar Wiki for Call for Papers WorldCat Zenodo

Aegis-AI: An Intelligent Scam Detection and Conversational Honeypot System for Cyber Threat Investigation

Author(s) Mr. Lakshminarayanan E, Mr. Naresh S, Mr. Naveen K, Mrs. Meena V
Country India
Abstract Digital scams frequently rely on impersonation, urgent instructions, requests for one-time passwords (OTPs), payment demands, and suspicious links to manipulate people through online communication channels. Although message classifiers can identify suspicious content, effective investigation also requires preserving conversation context, extracting relevant indicators, assessing potential risks, and organizing evidence. This paper presents Aegis-AI, an intelligent scam detection and conversational honeypot system designed to integrate these activities into a unified investigation workflow. The system uses a Flutter-based client connected to a Python FastAPI backend, with Google Gemini supporting context-aware conversational responses and Firebase Firestore serving as the proposed storage layer. The documented backend implementation includes keyword-based scam detection, regular-expression extraction of Indian-format mobile numbers, URLs and UPI-like identifiers, and a weighted risk assessment mechanism. Based on predefined indicator weights and thresholds, messages are classified into low, medium, or high-risk categories. The system also supports session-based conversation handling and structured investigation reporting. However, the available project documentation does not include a labelled evaluation dataset or measured performance metrics such as accuracy, precision, recall, and F1-score. Therefore, this paper focuses on the system architecture, implementation, and functional capabilities while outlining an evaluation approach for future validation.
Keywords Scam Detection, Conversational Honeypot, Cybersecurity, Threat Intelligence, Risk Assessment, Large Language Models, FastAPI, Session Management
Field Computer > Network / Security
Published In Volume 7, Issue 6, November-December 2026
Published On 2026-11-04
View / Download PDF File

Share this



E-ISSN 3048-7641
CrossRef

CrossRef DOI is assigned to each research paper published in our journal.

AIJFR DOI prefix is
10.63363/aijfr

Downloads
Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 7 Isu 6Cover Page Vol 7 Isu 4Cover Page Vol 7 Isu 3

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA Open Access

About AIJFR
Fees & Payment
Current Issue
Publication Archive 		Submit Research Paper
Track Submission Status
Publication Guidelines
Publication Ethics
Peer Review & Plagiarism 		Join as a Reviewer
Editors & Reviewers
Reviewer Referral Program
Get Reviewer Membership Certi. 		Website/Journal Policies
Usage Policy
Content Policies
Privacy Policy
Contact Us +91-9898-79-39-59 editor@aijfr.com