Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs

Abstract

Large Language Models (LLMs) are increasingly integrated into consumer and enterprise applications. Despite their capabilities, they remain susceptible to adversarial attacks such as prompt injection and jailbreaks that override alignment safeguards. This paper provides a systematic investigation of jailbreak strategies against various state-of-the-art LLMs. We categorize over 1,400 adversarial prompts, analyze their success against GPT-4, Claude 2, Mistral 7B, and Vicuna, and examine their gene

Categories

Framework mappings

Suggested from the entry's categories.

@misc{pathade2025red,
  title = {{Red Teaming the Mind of the Machine: A Systematic Evaluation of Prompt Injection and Jailbreak Vulnerabilities in LLMs}},
  author = {Chetan Pathade},
  year = {2025},
  month = may,
  eprint = {2505.04806},
  archivePrefix = {arXiv},
  doi = {10.48550/arXiv.2505.04806},
  url = {https://www.semanticscholar.org/paper/46a9f0dc9f74bef40c2f860e604c338c8092d30e}
}