README.md

---
license: mit
language:
- en
---

# STEALTH 

*Secure Transformer for Encrypted Alignment of Latent Text Embeddings*.

![PyTorch](https://img.shields.io/badge/PyTorch-%3E%3D1.8-orange) ![Transformers](https://img.shields.io/badge/Transformers-compatible-blue) ![Hugging%20Face](https://img.shields.io/badge/Hugging%20Face-model-blueviolet) ![License: MIT](https://img.shields.io/badge/License-MIT-green) ![Model size](https://img.shields.io/badge/Model--size-120M-lightgrey)
## Model — short description

STEALTH is a **120M-parameter** transformer encoder trained to produce **encryption-invariant** sentence embeddings. It learns a topology-preserving mapping from encrypted text embeddings to a plaintext embedding space using the **Semantic Isomorphism Enforcement (SIE)** multi-objective loss. 

## Model specs

* **Architecture:** 12-layer Transformer encoder with key-attentive attention and multi-key aggregation. 
* **Model size:** ~**120M parameters**. 
* **Embedding dim (output):** 256. 
* **Tokenizer:** encryption-aware byte-level tokenizer. 

# Highlights

* ✅ **Privacy-first**: Operates on ciphertext without requiring decryption.
* ✅ **Topology preserving**: SIE loss aligns encrypted and plaintext embeddings while preserving semantic distances.
* ✅ **Robust training**: Multi-key augmentation (multiple ciphertext variants per plaintext) improves invariance and generalization.
* ✅ **Practical**: Small model footprint (120M) for efficient deployment in constrained environments.