# S3AT

**Repository Path**: wwenyuu/s3-at

## Basic Information

- **Project Name**: S3AT
- **Description**: code of S3AT
- **Primary Language**: Unknown
- **License**: OSL-3.0
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 1
- **Created**: 2025-05-25
- **Last Updated**: 2026-03-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# S3AT: Self-paced, Self-distilled, Self-finetuned Adversarial Training for Robust Automatic Modulation Recognition

We propose S3AT, a novel adversarial training framework that integrates Self-Paced learning, Self-Distillation, and Self-Finetuning. 

## Important Notice

This repository is currently in **pre-release status** as the associated academic paper is under review. 

## Project Overview

- **Research Field**: adversarial training, automatic modulation recognition
- **Key Technologies**: self-paced learning, self-distillation
- **Main Contributions**: robust recognition under adversarial attacks

## Released Contents

After paper publication, this repository will include:
- Full model implementation
- Training and evaluation scripts
- Detailed documentation

## Citation

If this project aids your research, please consider citing our paper:

```bibtex
["To be added"]