Towards Near-imperceptible Steganographic Text (P19-1)

Copied to clipboard

Challenge: Existing methods for linguistic steganography are vulnerable to automated detection.
Approach: They propose an encoding algorithm with improved near-imperceptible guarantees based on implicit assumptions on statistical behaviors of fluent text.
Outcome: The proposed algorithm improves on existing steganographic systems with near-imperceptible guarantees.

Similar Papers

Frustratingly Easy Edit-based Linguistic Steganography with a Masked Language Model (2021.naacl-main)

Copied to clipboard

Challenge: linguistic steganography is the practice of concealing a secret message in some cover data such that an eavesdropper is not even aware of the existence of the secret message.
Approach: They propose to use edit-based linguistic steganography to generate genuine-looking texts by using a masked language model that eliminates painstaking rule construction and has a high payload capacity.
Outcome: The proposed method eliminates painstaking rule construction and has a high payload capacity for an edit-based model.
Near-imperceptible Neural Linguistic Steganography via Self-Adjusting Arithmetic Coding (2020.emnlp-main)

Copied to clipboard

Challenge: Linguistic steganography studies how to hide secret messages in natural language cover texts.
Approach: They propose a method which encodes secret messages using self-adjusting arithmetic coding based on a neural language model.
Outcome: The proposed method outperforms the state-of-the-art methods on four datasets by 15.3% and 38.9% in terms of bits/word and KL metrics.
Addressing Segmentation Ambiguity in Neural Linguistic Steganography (2022.aacl-short)

Copied to clipboard

Challenge: Recent studies on neural linguistic steganography ignore the fact that the sender must detokenize cover texts to avoid arousing the eavesdropper’s suspicion.
Approach: They propose to decode a secret message in a way that does not arouse suspicion of the eavesdropper.
Outcome: The proposed techniques are applicable to languages without explicit word boundaries.
Addressing Tokenization Inconsistency in Steganography and Watermarking Based on Large Language Models (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models have improved the capacities and efficiency of text generation.
Approach: They propose a method for tokenization inconsistency and a watermarking technique to address this problem.
Outcome: The proposed methods improve fluency, imperceptibility, and anti-steganalysis capacity.
Efficient Provably Secure Linguistic Steganography via Range Coding (2026.acl-long)

Copied to clipboard

Challenge: Linguistic steganography is a promising field in safeguarding information . previous methods have achieved perfect imperceptibility but at the expense of embedding capacity.
Approach: They propose to use a classical entropy coding method to achieve secure steganography . they propose to employ a rotation mechanism to achieve embedding efficiency .
Outcome: The proposed method outperforms existing methods in embedding capacity and embeddability.
Look Who’s Talking Now: Covert Channels From Biased LLMs (2024.findings-emnlp)

Copied to clipboard

Challenge: steganography encodes hidden messages into model-generated tokens . tradeoff between how much hidden information can be introduced and how much the model can be perturbed is important .
Approach: They propose to use large language model-based steganography to encode hidden messages into model-generated tokens.
Outcome: The proposed techniques are nearly optimal under a practical but difficult set of constraints . the proposed techniques ensure that only someone with the appropriate decoding key can access the hidden information .
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) (2023.acl-demo)

Copied to clipboard

Challenge: 58 papers were selected for inclusion in the program, while a small number received only two reviews.
Approach: the 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023) will be held in london from July 9-14, 2023 . 58 submissions were selected for inclusion in the program, with an acceptance rate of 37%)
Outcome: the system demonstration track received a record number of submissions . 58 papers were selected for inclusion in the program .
Proceedings of the First Workshop on Commonsense Inference in Natural Language Processing (D19-60)

Copied to clipboard

Challenge: Workshop on Commonsense Inference in Natural Language Processing focuses on commonsense knowledge representation and application in NLP tasks.
Approach: COIN is a workshop on commonsense inference in natural language processing . workshop included two shared tasks on reading comprehension using commonsensense knowledge .
Outcome: the workshop focused on modeling commonsense knowledge and commonsensing in natural language processing tasks.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) (2026.acl-demo)

Copied to clipboard

Challenge: ACL 2026 System Demonstration Track accepted 85 papers . one paper received Best Demo award .
Approach: the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026) took place from July 2-7, 2026 in San Diego, California.
Outcome: the ACL 2026 System Demonstration Track accepted 85 papers based on the submitted reviews . one paper received the best demo award: The olmOCR Project: Building Fully Open OCR using VLMs .
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations) (2025.acl-demo)

Copied to clipboard

Challenge: ACL 2025 System Demonstration Track accepted 64 papers based on reviews . short-listed 7 papers for Best System Demo award .
Approach: the ACL 2025 System Demonstration Track is a conference for papers describing system demonstrations . the track received a record 187 submissions, of which 178 papers were valid with required materials .
Outcome: the ACL 2025 System Demonstration Track received 187 submissions . 178 papers were valid with required materials .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations