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.
@article{arxiv.2411.14502,
title = {Global Challenge for Safe and Secure LLMs Track 1},
author = {Xiaojun Jia and Yihao Huang and Yang Liu and Peng Yan Tan and Weng Kuan Yau and Mun-Thye Mak and Xin Ming Sim and Wee Siong Ng and See Kiong Ng and Hanqing Liu and Lifeng Zhou and Huanqian Yan and Xiaobing Sun and Wei Liu and Long Wang and Yiming Qian and Yong Liu and Junxiao Yang and Zhexin Zhang and Leqi Lei and Renmiao Chen and Yida Lu and Shiyao Cui and Zizhou Wang and Shaohua Li and Yan Wang and Rick Siow Mong Goh and Liangli Zhen and Yingjie Zhang and Zhe Zhao},
journal= {arXiv preprint arXiv:2411.14502},
year = {2024}
}