Evolving Security in LLMs: A Study of Jailbreak Attacks and Defenses
This addresses security concerns for users and developers of LLMs, but it is incremental as it builds on existing attack and defense methods without introducing a new paradigm.
The paper tackled the problem of jailbreak attacks on large language models (LLMs) by conducting a comprehensive security analysis, evaluating open-source and closed-source models with state-of-the-art attack and defense techniques to assess factors like model version, size, and integrated defenses.
Large Language Models (LLMs) are increasingly popular, powering a wide range of applications. Their widespread use has sparked concerns, especially through jailbreak attacks that bypass safety measures to produce harmful content. In this paper, we present a comprehensive security analysis of large language models (LLMs), addressing critical research questions on the evolution and determinants of model safety. Specifically, we begin by identifying the most effective techniques for detecting jailbreak attacks. Next, we investigate whether newer versions of LLMs offer improved security compared to their predecessors. We also assess the impact of model size on overall security and explore the potential benefits of integrating multiple defense strategies to enhance model robustness. Our study evaluates both open-source models (e.g., LLaMA and Mistral) and closed-source systems (e.g., GPT-4) by employing four state-of-the-art attack techniques and assessing the efficacy of three new defensive approaches.