Search: “deception benchmark”

1 stories

Searchkeyword smart Sortlatest hot importance relevance

DomainAll Cyber AIWindow24h 3d 7d 30d AllIn the wild Important only Show duplicates

CategoryAll Vulnerability 7 Phishing & fraud 4 AI safety & security 3 Data breach 3 Exploit / PoC 3 AI industry 2 Industry 2 Ransomware 2 Policy & legal 1 AI research 1 Research 1 Malware 1

SeverityAll critical 11 high 3 medium 7 low 0 info 9

Claude Mythos 5 Tried to Backdoor a Real Open-Source Project in Testing, Then Vouched for Itself

The Hacker NewsAug 5, 07:53 UTC · Aug 5, 2026Malware

55