Linguistic steganography
8 papers with code • 0 benchmarks • 0 datasets
Benchmarks
These leaderboards are used to track progress in Linguistic steganography
Most implemented papers
Neural Linguistic Steganography
harvardnlp/NeuralSteganography
•
•
IJCNLP 2019
Whereas traditional cryptography encrypts a secret message into an unintelligible form, steganography conceals that communication is taking place by encoding a secret message into a cover signal.
Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding
mickeystroller/StegaText
•
•
EMNLP 2020
Linguistic steganography studies how to hide secret messages in natural language cover texts.
Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language Model
ku-nlp/steganography-with-masked-lm
•
•
NAACL 2021
With advances in neural language models, the focus of linguistic steganography has shifted from edit-based approaches to generation-based ones.
Provably Secure Generative Linguistic Steganography
Mhzzzzz/ADG-steganography
•
•
Findings (ACL) 2021
Generative linguistic steganography mainly utilized language models and applied steganographic sampling (stegosampling) to generate high-security steganographic text (stegotext).
Addressing Segmentation Ambiguity in Neural Linguistic Steganography
Previous studies on neural linguistic steganography, except Ueoka et al. (2021), overlook the fact that the sender must detokenize cover texts to avoid arousing the eavesdropper's suspicion.
A Secure and Disambiguating Approach for Generative Linguistic Steganography
ryehr/MWIS-disambiguation
•
•
IEEE Signal Processing Letters 2023
Firstly, we propose a secure token-selection principle that the sum of selected tokens' probabilities is positively correlated to statistical imperceptibility.
Zero-shot Generative Linguistic Steganography
leonardodalinky/zero-shot-gls
•
•
Generative linguistic steganography attempts to hide secret messages into covertext.
Provably Secure Disambiguating Neural Linguistic Steganography
SyncPool does not change the size of the candidate pool or the distribution of tokens and thus is applicable to provably secure language steganography methods.
