# CyberSecEval 2 - A Comprehensive Evaluation Framework for Cybersecurity Risks and Capabilities of Large Language Models

DevFeed: [CyberSecEval 2 - A Comprehensive Evaluation Framework for Cybersecurity Risks and Capabilities of Large Language Models](<https://devfeed.tech/articles/cyberseceval-2-a-comprehensive-evaluation-framework-for-cybersecurity-risks-and-capabilities-of-large-language-models-7321.md>)

Original publisher: [Read original article](<https://huggingface.co/blog/leaderboard-llamaguard>)

Author: r34p3r; Sahana C; Yue; Cyrus Nikolaidis; Daniel Song; Simon Wan; Faizan Ahmad; cornelius aschermann; Yaohui Chen; Dhaval Kapil

Published: 2024-05-24T00:00:00Z

Content type: article

Language: en

Sources: [Hugging Face - Blog](<https://devfeed.tech/sources/hugging-face-blog.md>)

Topics: [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>), [Security & Privacy](<https://devfeed.tech/topics/security-privacy.md>), [prompt injection](<https://devfeed.tech/topics/prompt-injection.md>), [Security Attacks](<https://devfeed.tech/topics/security-attacks.md>), [Open Source](<https://devfeed.tech/topics/open-source.md>)

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [leaderboard](<https://devfeed.tech/tags/leaderboard.md>), [llm](<https://devfeed.tech/tags/llm.md>), [nlp](<https://devfeed.tech/tags/nlp.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [prompt-injection](<https://devfeed.tech/tags/prompt-injection.md>), [research](<https://devfeed.tech/tags/research.md>), [security](<https://devfeed.tech/tags/security.md>)

## AI overview

CyberSecEval 2 is an evaluation framework for measuring cybersecurity risks and capabilities in large language models. It covers insecure code generation, prompt-injection resilience, cyberattack compliance, code-interpreter abuse, and automated offensive cybersecurity tasks, including SQL injection and buffer-overflow exercises.

## Source excerpt

We're on a journey to advance and democratize artificial intelligence through open source and open science.