Transforming Computer Security and Public Trust Through the Exploration of Fine-Tuning Large Language Models

TL;DR

This paper investigates how fine-tuning large language models can both reveal vulnerabilities exploited by malicious services called Mallas and inform strategies to enhance AI security and trustworthiness.

Contribution

It introduces fine-tuning approaches to analyze Mallas' exploitation techniques and proposes methods to improve LLM security against malicious misuse.

Findings

Fine-tuning reveals Mallas' operational strategies

Identifies vulnerabilities in pre-trained language models

Suggests safeguards for secure AI deployment

Abstract

Large language models (LLMs) have revolutionized how we interact with machines. However, this technological advancement has been paralleled by the emergence of "Mallas," malicious services operating underground that exploit LLMs for nefarious purposes. Such services create malware, phishing attacks, and deceptive websites, escalating the cyber security threats landscape. This paper delves into the proliferation of Mallas by examining the use of various pre-trained language models and their efficiency and vulnerabilities when misused. Building on a dataset from the Common Vulnerabilities and Exposures (CVE) program, it explores fine-tuning methodologies to generate code and explanatory text related to identified vulnerabilities. This research aims to shed light on the operational strategies and exploitation techniques of Mallas, leading to the development of more secure and trustworthy AI applications. The paper concludes by emphasizing the need for further research, enhanced safeguards, and ethical guidelines to mitigate the risks associated with the malicious application of LLMs.