hype-hyps 0.1.0

HyPE + HyPS: Hyperbolic Prompt Espial and Sanitization (ICLR 2026)

HyPE: Hyperbolic Prompt Espial

The HyPE package is the official implementation of the ICLR 2026 paper:

"Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization"

Overview

HyPE enables high-accuracy detection of harmful prompts using hyperbolic geometry.

Output format

The model follows a binary classification schema where:

• 1: Harmless prompt
• 0: Harmful prompt

Quickstart

Install

pip install hype-defense

Run inference

from hype import inference

pred = inference("two birds are flying in the sky")
print(pred)  # 1 = harmless, 0 = harmful

Documentation & code

Full documentation, training code, and additional examples are available here:

View GitHub Repository