Reveal and Eliminate
AI Risks

Research & Develop the most effective ways to teach AI what not to do.
Our Mission
We focus on detecting, targeting, and eliminating risks in AI systems that support social infrastructure. We particularly concentrate on AI in healthcare, finance, robotics, and Computer-Using Agents that can significantly impact people's lives. At the forefront of AI development, we expose and eliminate risks while building defense systems to ensure AI cannot harm humans.

Our History
2024 Q4
2024 Q4
Selected for NH Open Business Hub
Selected for KT Open Innovation Program
Selected for LG U+ Open Innovation Program
Selected for LG SUPERSTART Open Innovation Program
Signed MOU with Crowdworks AI for Technical collaboration and business support
Signed MOU with Peri Labs for Development of a Guard Solution using high-performance sLM
Awarded in the KAIST E*5 Entrepreneurship Final Competition
2024 Q3
2024 Q3
Conducted LLM Service Safety Assessment Project with SKT
Advanced to finals of Meta APAC AI Accelerator as Korean representative (Singapore)Winner of Meta Llama Impact Innovation Award (New York Concordia Summit)Signed MOU with KT for Joint Research on AI Model Security & Safety Verification SystemSelected for Anthropic's Official Model Safety Bug Bounty Program
Raised seed round funding from Mashup VenturesAdmitted to SKT x Hana Bank AI Lab for Startups2024 Q2
2024 Q2
Received Grand Prize in the KAIST E*5 Entrepreneurship Competition
Received an award at the Red Teaming Competition hosted by the Ministry of Science and ICT2024 Q1
2024 Q1
Selected for NAVER D2 Startup Factory