benchmark

CyberSecEval 2

benchmarkactivecyberseceval-2-c471014b·1 events·first seen 28d ago

Aliases: CyberSecEval 2

Co-occurring entities

More like this (12)

Cyber Verification Program Cybersecurity Task Evaluation AlpacaEval 2 U.S. Cyber Command OpenAI Cybersecurity Grant Program AI Cybersecurity Threat Evaluation Framework CybORG CAGE-2 CVSS-C Center for Security and Emerging Technology SIMA 2 US Cyber and AI Safety Institute SafeCoder

Recent events (1)

5Hugging Face Blog·28d ago·source ↗

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

CyberSecEval 2 is a benchmark framework designed to evaluate both the cybersecurity risks and capabilities of large language models. The framework appears to be hosted or featured on Hugging Face's leaderboard infrastructure, extending prior cybersecurity evaluation work. It assesses LLMs across multiple dimensions of security-relevant behavior, including potential for misuse and defensive capabilities.

Evaluation and Benchmarking AI Safety Research CyberSecEval 2 LlamaGuard Hugging Face +1 more