Unknown
rss_securityweek
·
rss_8f509feee2e4b2b89226d7f0e16fe76a
Nuclear-Sabotage Malware Benchmark Trips Up Most Frontier AI Models
Published Jul 23, 2026
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.
Affected AI Products
ai model