A CIA Triad-Based Taxonomy of Prompt Attacks on Large Language Models

Nicholas Jones, Md Whaiduzzaman, Tony Jan (), Amr Adel, Ammar Alazab () and Afnan Alkreisat
Additional contact information
Nicholas Jones: Centre for Artificial Intelligence Research and Optimization (AIRO), Design and Creative Technology Vertical, Torrens University Australia, Ultimo, NSW 2007, Australia
Md Whaiduzzaman: Centre for Artificial Intelligence Research and Optimization (AIRO), Design and Creative Technology Vertical, Torrens University Australia, Ultimo, NSW 2007, Australia
Tony Jan: Centre for Artificial Intelligence Research and Optimization (AIRO), Design and Creative Technology Vertical, Torrens University Australia, Ultimo, NSW 2007, Australia
Amr Adel: Centre for Artificial Intelligence Research and Optimization (AIRO), Design and Creative Technology Vertical, Torrens University Australia, Ultimo, NSW 2007, Australia
Ammar Alazab: Centre for Artificial Intelligence Research and Optimization (AIRO), Design and Creative Technology Vertical, Torrens University Australia, Ultimo, NSW 2007, Australia
Afnan Alkreisat: CyberNex, Somerton, VIC 3062, Australia

Future Internet, 2025, vol. 17, issue 3, 1-28

Abstract: The rapid proliferation of Large Language Models (LLMs) across industries such as healthcare, finance, and legal services has revolutionized modern applications. However, their increasing adoption exposes critical vulnerabilities, particularly through adversarial prompt attacks that compromise LLM security. These prompt-based attacks exploit weaknesses in LLMs to manipulate outputs, leading to breaches of confidentiality, corruption of integrity, and disruption of availability. Despite their significance, existing research lacks a comprehensive framework to systematically understand and mitigate these threats. This paper addresses this gap by introducing a taxonomy of prompt attacks based on the Confidentiality, Integrity, and Availability (CIA) triad, an important cornerstone of cybersecurity. This structured taxonomy lays the foundation for a unique framework of prompt security engineering, which is essential for identifying risks, understanding their mechanisms, and devising targeted security protocols. By bridging this critical knowledge gap, the present study provides actionable insights that can enhance the resilience of LLM to ensure their secure deployment in high-stakes and real-world environments.

Keywords: large language model; prompt security engineering; prompt attack; CIA triad; taxonomy; mitigation protocols (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/17/3/113/pdf (application/pdf)
https://www.mdpi.com/1999-5903/17/3/113/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:17:y:2025:i:3:p:113-:d:1604360

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().