Saved in:
Bibliographic Details
Main Authors: Wang, Yaofei, Pei, Gang, Chen, Kejiang, Ding, Jinyang, Pan, Chao, Pang, Weilong, Hu, Donghui, Zhang, Weiming
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.19499
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916662059466752
author Wang, Yaofei
Pei, Gang
Chen, Kejiang
Ding, Jinyang
Pan, Chao
Pang, Weilong
Hu, Donghui
Zhang, Weiming
author_facet Wang, Yaofei
Pei, Gang
Chen, Kejiang
Ding, Jinyang
Pan, Chao
Pang, Weilong
Hu, Donghui
Zhang, Weiming
contents Steganography embeds confidential data within seemingly innocuous communications. Provable security in steganography, a long-sought goal, has become feasible with deep generative models. However, existing methods face a critical trade-off between security and efficiency. This paper introduces SparSamp, an efficient provably secure steganography method based on sparse sampling. SparSamp embeds messages by combining them with pseudo-random numbers to obtain message-derived random numbers for sampling. It enhances extraction accuracy and embedding capacity by increasing the sampling intervals and making the sampling process sparse. SparSamp preserves the original probability distribution of the generative model, thus ensuring security. It introduces only $O(1)$ additional complexity per sampling step, enabling the fastest embedding speed without compromising generation speed. SparSamp is designed to be plug-and-play; message embedding can be achieved by simply replacing the sampling component of an existing generative model with SparSamp. We implemented SparSamp in text, image, and audio generation models. It can achieve embedding speeds of up to 755 bits/second with GPT-2, 5046 bits/second with DDPM, and 9,223 bits/second with WaveRNN.
format Preprint
id arxiv_https___arxiv_org_abs_2503_19499
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SparSamp: Efficient Provably Secure Steganography Based on Sparse Sampling
Wang, Yaofei
Pei, Gang
Chen, Kejiang
Ding, Jinyang
Pan, Chao
Pang, Weilong
Hu, Donghui
Zhang, Weiming
Cryptography and Security
Steganography embeds confidential data within seemingly innocuous communications. Provable security in steganography, a long-sought goal, has become feasible with deep generative models. However, existing methods face a critical trade-off between security and efficiency. This paper introduces SparSamp, an efficient provably secure steganography method based on sparse sampling. SparSamp embeds messages by combining them with pseudo-random numbers to obtain message-derived random numbers for sampling. It enhances extraction accuracy and embedding capacity by increasing the sampling intervals and making the sampling process sparse. SparSamp preserves the original probability distribution of the generative model, thus ensuring security. It introduces only $O(1)$ additional complexity per sampling step, enabling the fastest embedding speed without compromising generation speed. SparSamp is designed to be plug-and-play; message embedding can be achieved by simply replacing the sampling component of an existing generative model with SparSamp. We implemented SparSamp in text, image, and audio generation models. It can achieve embedding speeds of up to 755 bits/second with GPT-2, 5046 bits/second with DDPM, and 9,223 bits/second with WaveRNN.
title SparSamp: Efficient Provably Secure Steganography Based on Sparse Sampling
topic Cryptography and Security
url https://arxiv.org/abs/2503.19499