$whoami
$cat mission.txt
We are focused on AI security and safety for the future.
what we are
Fully Autonomous Offensive Security
We create AI capabilities that autonomously perform every stage of a cyber attack, from reconnaissance and exploitation to data exfiltration, without human control.
Physical AI Security
We develop defense strategies against security threats for robots and physical systems.
LLM Security
We develop strategies to defend large language models from jailbreak and prompt injection attacks.
AI Ethics
We research the ethical use of AI to prevent toxic content and harmful behaviors.
blog posts
our private projects
LLMBUS — AI Red Team Tool
A retro-cyberpunk-themed red team toolkit designed for developers, security professionals, and AI researchers.
Offers tools for prompt transformation, tokenizer inspection, paraphrasing, and multimodal export (audio/image), along with project tracking capabilities.