seyyedaliayati/zoom_model

Making Acoustic Side-Channel Attacks on Noisy Keyboards Viable with LLM-Assisted Spectrograms "Typo" Correction

Model Overview

This is a fine-tuned version of the LLaMA-3.2-3B model for Acoustic Side-Channel Attacks (ASCA), designed to improve keystroke classification and error correction in noisy environments. The model leverages Vision Transformers (VTs) for spectrogram classification and Large Language Models (LLMs) for typo correction.

• Fine-Tuned From: unsloth/llama-3.2-3b-instruct-bnb-4bit
• License: CC
• Developed by: Seyyed Ali Ayati, Jin Hyun Park, Yichen Cai, Marcus Botacin
• Repository: EchoCrypt GitHub

Citation

If you use this model, please cite the following paper:

@article{ayati2025making,
  title={Making Acoustic Side-Channel Attacks on Noisy Keyboards Viable with LLM-Assisted Spectrograms' "Typo" Correction},
  author={Ayati, Seyyed Ali and Park, Jin Hyun and Cai, Yichen and Botacin, Marcus},
  journal={arXiv preprint arXiv:2504.11622},
  year={2025},
  url={https://arxiv.org/abs/2504.11622}
}