AI-driven analytical study on intelligent systems for detecting fake and fraudulent phone calls

Read full text Summarise with VIRAT
Authors: Parvinder Kumar, Kamna Solanki
Cited by: 0
References: 26

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Fraudulent and spam phone calls have grown into a major security challenge as scammers now use advanced tools such as AI-generated voices, caller ID spoofing and automated robocall systems. This study examines intelligent methods for detecting these threats by integrating machine learning, deep learning and signal-processing techniques. Metadata from call records, acoustic features from voice signals and linguistic patterns from transcripts are analyzed together to identify suspicious behavior. Modern models such as CNNs, BiLSTMs and multimodal fusion systems show strong capability to recognize robocalls, voice phishing attempts and AI-driven scam conversations in real time. The study highlights the strengths and limitations of each approach and emphasizes the need for hybrid, scalable and privacy-preserving solutions. AI-driven detection frameworks provide a promising path to reduce fraudulent calls and enhance user safety.

Fields of Study & Subjects

Spam and Phishing Detection Speech Recognition and Synthesis Misinformation and Its Impacts

Publication details

Journal / source
International Journal of Cloud Computing and Database Management
Volume
7
Issue
1
Pages
109–117
Publication date
1 January 2026
Language
EN