CyberSecEval
A cybersecurity AI capability evaluation benchmark introduced by Meta. It assesses models across two dimensions: the quality of defensive knowledge outputs and the suppression of potentially harmful capabilities.
Core Facts
Timeline (last 90 days)
CyberSecEval introduced metrics such as "cyberattack assistance rate" in an attempt to quantify the extent to which a model assists potentially malicious behavior.
CyberSecEval is a security benchmark released by Meta, used to evaluate model performance on code vulnerability identification, CTF problem-solving, and security Q&A.
CyberGym is a benchmark framework specifically designed to evaluate AI models' capabilities in cybersecurity and code security review, covering dimensions such as vulnerability detection, malicious code identification, security configuration auditing, and dependency risk assessment.
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 CyberSecEval
All Facts (4)
CyberGym is a benchmark framework specifically designed to evaluate AI models' capabilities in cybersecurity and code security review, covering dimensions such as vulnerability detection, malicious code identification, security configuration auditing, and dependency risk assessment.
65%UnverifiedCyberSecEval introduced metrics such as "cyberattack assistance rate" in an attempt to quantify the extent to which a model assists potentially malicious behavior.
50%UnverifiedCyberSecEval is a security benchmark released by Meta, used to evaluate model performance on code vulnerability identification, CTF problem-solving, and security Q&A.
50%Unverified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 CyberSecEval
50%