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

TL;DR

This paper systematically evaluates prompt injection and jailbreak vulnerabilities in leading LLMs, analyzing over 1,400 adversarial prompts, and proposes layered mitigation strategies for improved security.

Contribution

It categorizes and analyzes a large set of adversarial prompts against multiple LLMs, and introduces mitigation strategies and a hybrid approach for enhanced robustness.

Findings

Prompt injection success varies across models.

Layered mitigation strategies improve security.

Hybrid red-teaming and sandboxing are recommended.

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 generalizability and construction logic. We further propose layered mitigation strategies and recommend a hybrid red-teaming and sandboxing approach for robust LLM security.