Year: 2025
Type: preprint
Abstract: This paper introduces a novel self-consciousness defense mechanism for Large Language Models (LLMs) to combat prompt injection attacks. Unlike traditional approaches that rely on external classifiers, our method leverages the LLM's inherent reasoning capabilities to perform self-protection. We propose a framework that incorporates Meta-Cognitive and Arbitration Modules, enabling LLMs to evaluate and regulate their own outputs autonomously. Our approach is evaluated on seven state-of-the-art LLMs using two datasets: AdvBench and Prompt-Injection-Mixed-Techniques-2024. Experiment results demonstrate significant improvements in defense success rates across models and datasets, with some achieving perfect and near-perfect defense in Enhanced Mode. We also analyze the trade-off between defense success rate improvement and computational overhead. This self-consciousness method offers a lightweight, cost-effective solution for enhancing LLM ethics, particularly beneficial for GenAI use cases across various platforms.
Source: arXiv (Cornell University)
Authors: Huang, Boshi, de Paula, Fabio Nonato
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4414813401
Cites:
Cited by:
Related to: