leonardodalinky/zero-shot-GLS
[NAACL'24] ZGLS: Zero-shot Generative Linguistic Steganography
This project helps researchers and developers embed hidden information within seemingly normal text generated by large language models, without prior training on specific cover messages. It takes a secret message and plain text (like an email or article) as input, producing a new version of the plain text that subtly conceals the secret. This is useful for individuals needing to transmit covert information while maintaining the naturalness of the communication.
No commits in the last 6 months.
Use this if you need to hide secret messages within naturally sounding generated text without requiring pre-existing examples of hidden messages.
Not ideal if your primary goal is robust encryption against sophisticated cryptanalysis or if you need to hide information in non-textual data.
Stars
9
Forks
—
Language
Python
License
MIT
Category
Last pushed
Jan 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/leonardodalinky/zero-shot-GLS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
thunlp/OpenAttack
An Open-Source Package for Textual Adversarial Attack.
thunlp/TAADpapers
Must-read Papers on Textual Adversarial Attack and Defense
jind11/TextFooler
A Model for Natural Language Attack on Text Classification and Inference
thunlp/OpenBackdoor
An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)
thunlp/HiddenKiller
Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks...