A Linguistic Analysis of Prompt Injection in Large Language Models

Priscilla Adenuga


Abstract
Large Language Models (LLMs) are increasingly deployed across a wide range of applications, from conversational assistants to decision support systems. However, these systems remain vulnerable to prompt injection attacks, in which carefully crafted inputs manipulate model behavior and circumvent intended safeguards. While existing research has largely approached prompt injection as a technical or security problem, the linguistic mechanisms through which such attacks operate remain insufficiently understood. In this paper, we argue that prompt injection attacks are fundamentally linguistic in nature, exploiting discourse structure, pragmatic framing, and instruction hierarchies encoded in natural language prompts. Drawing on concepts from speech act theory, discourse analysis, and pragmatics, we propose a typology of four linguistic strategies used to manipulate Large Language Models: instruction override, role framing, hypothetical framing, and procedural prompting. Through detailed linguistic analysis of representative examples, we demonstrate how each strategy exploits identifiable properties of natural language interaction to reshape model interpretation and influence output generation. For each strategy, we also discuss implications for detection and mitigation, arguing that effective safeguards must attend to discourse-level patterns in prompts rather than relying solely on surface-level keyword filtering. Our findings contribute to emerging research at the intersection of computational linguistics and AI security and highlight the importance of integrating linguistic expertise into the design of more robust and reliable language-based AI systems.
Anthology ID:
2026.nlpaics-1.17
Volume:
Proceedings of the Second International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security
Month:
June
Year:
2026
Address:
Alicante, Spain
Editors:
Ruslan Mitkov, Rafael Muñoz, Elena Lloret, Tharindu Ranasinghe, Ernesto L. Estevanell-Valladares, Salima Lamsiyah, Andrés Montoyo, Saad Ezzini
Venue:
NLPAICS
SIG:
Publisher:
Department of Languages and Information Systems, University of Alicante
Note:
Pages:
163–170
Language:
URL:
https://aclanthology.org/2026.nlpaics-1.17/
DOI:
Bibkey:
Cite (ACL):
Priscilla Adenuga. 2026. A Linguistic Analysis of Prompt Injection in Large Language Models. In Proceedings of the Second International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security, pages 163–170, Alicante, Spain. Department of Languages and Information Systems, University of Alicante.
Cite (Informal):
A Linguistic Analysis of Prompt Injection in Large Language Models (Adenuga, NLPAICS 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.nlpaics-1.17.pdf