AI article

AX-RAY & K-MYTHOS: Inside Korea's Consortium-Built Security-Specialized AI Foundation Model

Community description: 네이버클라우드 주도 33개 기관 컨소시엄이 개발하는 K-MYTHOS 보안 AI 파운데이션 모델과 VIDRAFT의 AX-RAY 안전성 진단 프레임워크(117개 체크리스트)를 심층 분석합니다.

Dev.to | Sep 14, 2026 | AI OpenFree

Automated excerpt

VIDRAFT contributes AI safety diagnostics and evaluation via its AX-RAY framework, which covers 117 inspection checklist items. VIDRAFT's role in this consortium is AI safety diagnosis and evaluation. Rather than training a single monolithic model, the consortium separates offensive reasoning (attack AI on EXAONE) from defensive reasoning (defense AI on HyperCLOVA X).

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.

Read the original article

More AI news