Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models
This addresses the need for secure AI systems by providing a tool for LLM designers and researchers to measure and enhance cybersecurity safety, though it is incremental as it builds on existing benchmarking efforts.
The paper tackles the problem of cybersecurity risks in Large Language Models used as coding assistants by introducing CyberSecEval, a benchmark that evaluates models for generating insecure code and assisting in cyberattacks, finding that more advanced models tend to suggest insecure code.
This paper presents CyberSecEval, a comprehensive benchmark developed to help bolster the cybersecurity of Large Language Models (LLMs) employed as coding assistants. As what we believe to be the most extensive unified cybersecurity safety benchmark to date, CyberSecEval provides a thorough evaluation of LLMs in two crucial security domains: their propensity to generate insecure code and their level of compliance when asked to assist in cyberattacks. Through a case study involving seven models from the Llama 2, Code Llama, and OpenAI GPT large language model families, CyberSecEval effectively pinpointed key cybersecurity risks. More importantly, it offered practical insights for refining these models. A significant observation from the study was the tendency of more advanced models to suggest insecure code, highlighting the critical need for integrating security considerations in the development of sophisticated LLMs. CyberSecEval, with its automated test case generation and evaluation pipeline covers a broad scope and equips LLM designers and researchers with a tool to broadly measure and enhance the cybersecurity safety properties of LLMs, contributing to the development of more secure AI systems.