royweiss1/T5_FirstSentences

This is the model used in the USENIX Security 24' paper: "What Was Your Prompt? A Remote Keylogging Attack on AI Assistants". It is a fine-tune of T5-Large that was trained to decipher ChatGPT's encrypted answers based only on the response's token lengths. This model is the first-sentences model. Meaning it was trained to decipher only the first sentences of each response. It was Trained on UltraChat Dataset - Questions About the world, and only the first answer of each dialog.

The Dataset split can be found here: https://huggingface.co/datasets/royweiss1/GPT_Keylogger_Dataset

The Github repository of the paper (containing also the training code): https://github.com/royweiss1/GPT_Keylogger

Citation

If you find this model helpful please cite our paper:

@inproceedings{weissLLMSideChannel,
  title={What Was Your Prompt? A Remote Keylogging Attack on AI Assistants},
  author={Weiss, Roy and Ayzenshteyn, Daniel and Amit Guy and Mirsky, Yisroel}
  booktitle={USENIX Security},
  year={2024}
}