Cognitive Cyber Crimes in the Era of Artificial Intelligence

14AI-Generated Misinformation and Automated Psychological Warfare

Hitesh Rawat¹*, Anjali Rawat¹ and Anand Rajavat²

¹Computer Science Department, Shri Vaishnav Vidyapeeth Vishwavidyalaya, Indore, India

²Department of Computer Science Engineering, Shri Vaishnav Institute of Information Technology, Shri Vaishnav Vidyapeeth Vishwavidyalaya, Indore, India

Abstract

The proliferation of artificial intelligence (AI)–generated misinformation poses significant challenges to information integrity and national security. This study presents a novel approach to detecting AI-generated misinformation using the Annotated Misinformation, Media-Based (AMMeBa) dataset. We use a hybrid technique combining BERT (bidirectional encoder representations from transformers) and fine-tuned RoBERTa models to classify misinformation. Our method achieves an accuracy of 98.7%, precision of 98.5%, recall of 98.9%, and F1 score of 98.7%. Advanced parameters such as attention weights and contextual embeddings are utilized to enhance detection capabilities. The results demonstrate the efficacy of transformer-based models in identifying AI-generated misinformation, contributing to the development of automated psychological warfare countermeasures.

Keywords: AI-generated misinformation, psychological warfare, transformer models, BERT, RoBERTa

14.1 Introduction

The advent of generative artificial intelligence (AI) [1–4] technologies has revolutionized content creation, enabling the rapid production of realistic ...