AI brokers are more and more seen as a option to reinforce the capabilities of cybersecurity groups — however which may do the most effective job? Wiz has developed a benchmark suite of 257 real-world challenges spanning 5 offensive domains: zero-day discovery, CVE (code vulnerability) detection, API safety, internet safety, and cloud safety to search out out.
Wiz checks completely different combos of AI brokers and their underlying AI fashions in opposition to the check suite to see which rating the best in every of the 5 classes. Scoring is deterministic and programmatic utilizing a number of components: multi-dimensional rubrics for zero-day and CVE detection; endpoint-and-severity matching for API safety and lag seize for internet and cloud challenges.
The benchmark checks run inside remoted Docker containers with ample sources and no per-challenge timeouts, so scores replicate functionality relatively than throttling. Every agent makes use of its native instruments and execution mannequin out of the field, and will get three goes at each problem to see the way it performs on common.
