Unmasking Threat Vectors in Large Language Models: A Deep Analysis of Adversarial Exploitation

View Sample PDF

Author(s): Neeharika Joshi (Marwadi University, Rajkot, India), R. N. Ravikumar (Marwadi University, Rajkot, India), Satwik Kishore (Marwadi University, Rajkot, India), Sonukumar Pandit (Marwadi University, Rajkot, India), Shubhamkumar Pandit (Marwadi University, Rajkot, India)and S. Aarthi (Marwadi University, Rajkot, India)
Copyright: 2026
Pages: 34
Source title: Examining Vulnerabilities and Adversarial Exploitation of AI and LLMs
Source Author(s)/Editor(s): Puya Pakshad (Illinois Institute of Technology, USA)and Marwan Omar (Illinois Institute of Technology, USA)
DOI: 10.4018/979-8-3373-8252-4.ch001

Keywords: Artificial Intelligence / Engineering Science Reference / Information Security & Privacy / Security & Forensics

Purchase

View Unmasking Threat Vectors in Large Language Models: A Deep Analysis of Adversarial Exploitation on the publisher's website for pricing and purchasing information.

Abstract

AI-driven defect detection is increasingly essential as software systems grow in complexity, multilinguality, and scale. This chapter presents a comparative evaluation of traditional machine learning models and large language models for detecting structural and semantic defects across multiple programming languages. A multilingual dataset is used to assess Random Forest, SVM, XGBoost, and a prompt-based CodeT5 simulation, revealing the limitations of feature-engineered approaches and the superior semantic reasoning of LLMs. Practical integration scenarios in CI/CD, IDEs, and DevSecOps workflows are examined, followed by key challenges and emerging research directions for scalable, explainable, and automated defect detection.

The IRMA Community

Research IRM

Unmasking Threat Vectors in Large Language Models: A Deep Analysis of Adversarial Exploitation

Purchase

Abstract

Related Content

IRMA Sponsors