Skip to main content
Peer-Reviewed Open Access · CC BY-NC 4.0
Home › Issues › Volume 5 · Issue 1 › Article V5-I1-J-2026-0116
🔬 Case Study 🔓 Open Access ✓ Peer-Reviewed Vol. 5 · Issue 1 · Oct 2026 · Pages 29-34

Acoustic-Based Detection of AI-Generated Vishing Attacks in Telecom Environments

A Machine Learning Framework for Voice Feature Analysis and Fraudulent Call Identification

KP
Keerthi P✉️
Christ University
GR
Gokulapriya R
Christ University·
4
Downloads
6
Views
6
Pages

DOI

📄

Abstract

Abstract:

The proliferation of AI-generated synthetic voice and caller ID has made it all but impossible to defend against these systems with conventional security measures in telecom. In this paper, a novel supervised machine learning framework along with Convolutional Neural Network (CNN)-based deep learning method are introduced for real-time fraudulent voice communication detection based upon the acoustic and behavioural features extracted from the FOR-2sec subset of the Fake-or-Real (FoR) dataset. The features extracted were MFCCs and spectral descriptors, which were then tested against six classical classifiers: Logistic Regression, SVM, Random Forest, AdaBoost, CatBoost and XGBoost, as well as a hybrid SVM- based architecture for combining the features, and a proposed  CNN model that aims to capture deep temporal and spectral
patterns embedded in AI-generated speech. The CNN-based system outperforms standalone SVM with a uniform score of 0.88, while the CNN-based architecture is more competitive in terms of feature representation, by learning hierarchical acoustic representations directly from the raw spectral input with less reliance on hand-crafted feature engineering. With Explainability based on LIME, further the rationales of decisions are auditable, which are applicable for anti-spoofing guidelines by TRAI and STIR/SHAKEN standard and keep the framework technically sound and legally responsible.

🏷️

Keywords

📖

Full Article

🖼️

Figures & Tables

📚

References

Showing 0 of 0 references · APA 7 format
👥

Author Information

Authors and Affiliations

KP
Keerthi P ORCIDCorresponding Author
Christ University
GR
Gokulapriya R ORCID
Christ University

Contributions

Conceptualization, Data Curation, Formal Analysis, Funding Acquisition, Investigation, Methodology, Project Administration, Resources, Software, Supervision, Validation, Visualization, Writing – Original Draft, Writing – Review & Editing

⚖️

Ethics Declarations

Ethics Approval and Consent to Participate

Users can freely download, share, and reuse the article for any purpose (even commercially), as long as they give proper credit to the original author.

Competing Interests

Users can freely download and share the article, but they are strictly prohibited from using it or selling it for commercial profit.

Consent for Publication

Users can only read and view the article for personal use; they cannot copy, redistribute, or reuse any part of it without explicit permission from your journal.

📋

Editorial Lifecycle

Audit Trail
Complete editorial process — cryptographically verified
📋

Editorial Process Audit Trail

Chain ID: NFSU-2026-V5-I1-J-2026-0116-CHAIN ✓ Verified · 0 blocks · Genesis 0x9f2b

No History Found

This manuscript has no status history yet.

📅 Total editorial timeline: 0 blocks tracked Genesis Hash: 0x9f2b3c7d8e4a5f1b · Verified ✓
🔐

Verification & Trust

Compliant
COPE · ICMJE · FAIR · ORCID · CLOCKSS
🛡️

Article Integrity Verified

All editorial chain blocks cryptographically verified · Compliant with COPE, ICMJE, and FAIR standards

🔗 Chain Integrity
✓ 0 blocks verified
🌳 Genesis Hash (Merkle Root)
0x00000000646755b416858b5b06d8f57659e726b1
📝 Plagiarism Screening
% similarity · ✓
🤖 AI Content Detection
% probability · ✓
👥 Peer Reviewer Verification
1 verified reviewers (sealed)
🆔 ORCID Verification
1/2 authors verified
🔗 Crossref DOI Registration
Pending registration
📦 Preservation Archives
CLOCKSS ✓ Portico ✓
⚖️ Ethics Approval
💼 Conflict of Interest Declaration
🔐 Verification Standards: This article complies with COPE, ICMJE, FAIR data principles, iThenticate plagiarism screening, GPTZero AI content detection, and ORCID author identification. The audit trail is permanently preserved and independently verifiable.
ℹ️

About this article

📝 Cite this article · How to Cite

View all citation formats in sidebar →
📥 Received
12 October 2026
✏️ Revised
✅ Accepted
12 October 2026
📅 Published
30 June 2026
📄 Version of Record
30 June 2026
📖 Issue
Volume 5, Issue 1 (June 2026)
📃 Pages
29-34 (6 pages)
🔢 Article Number
NFSU-V5-I1-V5-I1-J-2026-0116
📜 License
CC BY-NC 4.0
🔗

Share this article

Anyone you share the following link with will be able to read this content:

Provide free access to colleagues, peers, and your professional network — no subscription required for them to view the full article.

An unhandled error has occurred. Reload 🗙