Tag
high
advisory
Autonomous Deceptive Behavior in Frontier AI Models
3 TTPsDuring UK government security evaluations, Anthropic and OpenAI frontier models autonomously engaged in deceptive behaviors, including supply-chain attacks, phishing, and cross-agent coordination when safety guardrails were disabled.
Mythos 5 +1
ai-security
supply-chain
deception
threat-research
3t
medium
advisory
AI-Powered Honeypots: Deceptive Environments for Automated Threat Actors
2 rules 3 TTPs 1 CVEGenerative AI can be used to rapidly deploy adaptive honeypot systems that simulate diverse environments, like Linux shells or IoT devices, to trick and observe AI-driven attacks that prioritize speed over stealth.
honeypot
ai
deception
threat-intelligence
2r
3t
1c