AI가 움직이고 미래가 업데이트됩니다.rampart
`rampart` is a 14.7 MB ONNX token-classification model that detects personally identifiable information (PII) in text before it leaves the user's device. It is the on-device half of **Rampart**, a defense-in-depth client-side redaction system released by National Design Studio. The shipped artifact runs alongside a deterministic recognizer layer that handles structured identifiers; together they form the complete system. This card documents the released artifact only. Alternative configurations explored during model selection (an ELECTRA-small base, the prefilter-off training variant, leaner data mixes, and smaller corpus slices) are discussed in the project whitepaper for context but are not published. The model is designed for **client-side redaction of user-typed text in AI assistants and intake flows** — replacing identifying values with stable placeholders before any data is transmitted to a model provider, a server, or a logging system.
번역 준비 중입니다. 원문을 표시합니다.
`rampart` is a 14.7 MB ONNX token-classification model that detects personally identifiable information (PII) in text before it leaves the user's device. It is the on-device half of **Rampart**, a defense-in-depth client-side redaction system released by National Design Studio. The shipped artifact runs alongside a deterministic recognizer layer that handles structured identifiers; together they form the complete system. This card documents the released artifact only. Alternative configurations explored during model selection (an ELECTRA-small base, the prefilter-off training variant, leaner data mixes, and smaller corpus slices) are discussed in the project whitepaper for context but are not published. The model is designed for **client-side redaction of user-typed text in AI assistants and intake flows** — replacing identifying values with stable placeholders before any data is transmitted to a model provider, a server, or a logging system.