Unverified50% confidenceFactExact time
CyberSecEval is a security benchmark released by Meta, used to evaluate model performance on code vulnerability identification, CTF problem-solving, and security Q&A.
1
Sources
50%
Confidence
Long-term
Relevance
9/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCyberSecEval由Meta推出，同时测量模型生成网络攻击辅助内容的风险倾向与安全防御知识的准确性；NYU CTF Bench基于真实CTF竞赛题目考察模型实战能力78% similarUnverifiedCyberGym是专门评估AI模型在网络安全和代码安全审查领域能力的基准框架，涵盖漏洞检测、恶意代码识别、安全配置审计、依赖项风险评估等维度76% similarUnverified网络安全能力基准测试的类似框架包括DARPA的Cyber Grand Challenge和Meta的PurpleLlama CyberSecEval73% similarUnverified评估模型安全能力的基准包括Meta推出的CyberSecEval和NYU CTF Bench70% similarUnverifiedCTF challenges cover areas including web security, reverse engineering, cryptography, binary exploitation (Pwn), and miscellaneous (Misc).69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/913322API
curl https://kongchang.com/api/v1/knowledge/claims/913322MCP
get_claim(id=913322)