Global Challenge for Safe and Secure LLMs Track 1

TL;DR

This paper presents a global challenge initiative aimed at developing automated methods to identify and improve the robustness of large language models against jailbreaking and adversarial attacks, crucial for safe deployment.

Contribution

It introduces a new competition framework focused on probing LLM vulnerabilities, fostering advancements in defense mechanisms against malicious exploitation.

Findings

Development of automated probing techniques for LLM vulnerabilities

Insights into common safety protocol bypass methods

Enhanced understanding of LLM robustness challenges

Abstract

This paper introduces the Global Challenge for Safe and Secure Large Language Models (LLMs), a pioneering initiative organized by AI Singapore (AISG) and the CyberSG R&D Programme Office (CRPO) to foster the development of advanced defense mechanisms against automated jailbreaking attacks. With the increasing integration of LLMs in critical sectors such as healthcare, finance, and public administration, ensuring these models are resilient to adversarial attacks is vital for preventing misuse and upholding ethical standards. This competition focused on two distinct tracks designed to evaluate and enhance the robustness of LLM security frameworks. Track 1 tasked participants with developing automated methods to probe LLM vulnerabilities by eliciting undesirable responses, effectively testing the limits of existing safety protocols within LLMs. Participants were challenged to devise techniques that could bypass content safeguards across a diverse array of scenarios, from offensive language to misinformation and illegal activities. Through this process, Track 1 aimed to deepen the understanding of LLM vulnerabilities and provide insights for creating more resilient models.