CYBERSECURITY
FEATURED ANALYSIS
Nuclear-Sabotage Malware Benchmark Trips Up Most Frontier AI Models
BY
Eduard Kovacs
SOURCE
SecurityWeek
DATE
READ
1 min read
SentinelOne’s new benchmark, built on the Fast16 case, shows which AI models can sustain a malware investigation and which cannot. The post Nuclear-Sabotage Malware Benchmark Trips Up Most Frontier AI Models appeared …
SentinelOne’s new benchmark, built on the Fast16 case, shows which AI models can sustain a malware investigation and which cannot. The post Nuclear-Sabotage Malware Benchmark Trips Up Most Frontier AI Models appeared first on SecurityWeek.