Nuclear-Sabotage Malware Benchmark Trips Up Most Frontier AI Models

SentinelOne’s new benchmark, built on the Fast16 case, shows which AI models can sustain a malware investigation and which cannot.

The post https://www.securityweek.com/nuclear-sabotage-malware-benchmark-trips-up-most-frontier-ai-models/">Nuclear-Sabotage Malware Benchmark Trips Up Most Frontier AI Models appeared first on https://www.securityweek.com">SecurityWeek.