Underground AI models promise to be hackers ‘cyber pentesting waifu’
Tier-based subscriptions, hacker specific training datasets and playful personalities are part of a growing underground criminal market for custom AI hacking tools.
Advertisement
large language models
New research finds that Claude breaks bad if you teach it to cheat
A new paper from Anthropic found that teaching Claude how to reward hack coding tasks caused the model to become less honest in other areas.
China’s ‘autonomous’ AI-powered hacking campaign still required a ton of human work
Anthropic and AI security experts told CyberScoop that behind the hype, effective AI-driven cyberattacks still require skilled humans, with the attack possibly done to send a message…
Researchers flag code that uses AI systems to carry out ransomware attacks
The malware, called PromptLock, essentially functions as a hard-coded prompt injection attack on a large language model, inspecting local filesystems, exfiltrating files and encrypting data.
Guess what else GPT-5 is bad at? Security
OpenAI and Microsoft have said that GPT-5 is one of their safest and secure models out of the box yet. An AI red-teamer called its performance “terrible.”