Related papers: A Plug-and-Play Method for Improving Imperceptibil…
Recent advances in linguistic steganalysis have successively applied CNN, RNN, GNN and other efficient deep models for detecting secret information in generative texts. These methods tend to seek stronger feature extractors to achieve…
Large language models are beginning to show steganographic capabilities. Such capabilities could allow misaligned models to evade oversight mechanisms. Yet principled methods to detect and quantify such behaviours are lacking. Classical…
Linguistic steganography involves embedding secret messages within seemingly innocuous texts to enable covert communication. Provable security, which is a long-standing goal and key motivation, has been extended to language-model-based…
Diffusion model-based generative image steganography (DM-GIS) is an emerging paradigm that leverages the generative power of diffusion models to conceal secret messages without requiring pre-existing cover images. In this paper, we identify…
Most of the existing text generative steganographic methods are based on coding the conditional probability distribution of each word during the generation process, and then selecting specific words according to the secret information, so…
An analysis of steganographic systems subject to the following perfect undetectability condition is presented in this paper. Following embedding of the message into the covertext, the resulting stegotext is required to have exactly the same…
Image steganography can hide information in a host image and obtain a stego image that is perceptually indistinguishable from the original one. This technique has tremendous potential in scenarios like copyright protection, information…
The rapid proliferation of frontier model agents promises significant societal advances but also raises concerns about systemic risks arising from unsafe interactions. Collusion to the disadvantage of others has been identified as a central…
Nowadays, social media has become the preferred communication platform for web users but brought security threats. Linguistic steganography hides secret data into text and sends it to the intended recipient to realize covert communication.…
Fine-tuned LLMs can covertly encode prompt secrets into outputs via steganographic channels. Prior work demonstrated this threat but relied on trivially recoverable encodings. We formalize payload recoverability via classifier accuracy and…
Generating high-quality steganographic text is a fundamental challenge in the field of generative linguistic steganography. This challenge arises primarily from two aspects: firstly, the capabilities of existing models in text generation…
We propose a simple universal (that is, distribution--free) steganographic system in which covertexts with and without hidden texts are statistically indistinguishable. The stegosystem can be applied to any source generating i.i.d.…
With the popularity of the large language models (LLMs), text steganography has achieved remarkable performance. However, existing methods still have some issues: (1) For the white-box paradigm, this steganography behavior is prone to…
Generative steganography is the process of hiding secret messages in generated images instead of cover images. Existing studies on generative steganography use GAN or Flow models to obtain high hiding message capacity and anti-detection…
Steganography is the art and science of hiding secret messages in public communication so that the presence of the secret messages cannot be detected. There are two distribution-preserving steganographic frameworks, one is sampling-based…
Linguistic steganography (LS) aims to embed secret information into a highly encoded text for covert communication. It can be roughly divided to two main categories, i.e., modification based LS (MLS) and generation based LS (GLS). Unlike…
Understanding and addressing potential safety alignment risks in large language models (LLMs) is critical for ensuring their safe and trustworthy deployment. In this paper, we highlight an insidious safety threat: a compromised LLM can…
Whereas cryptography easily arouses attacks by means of encrypting a secret message into a suspicious form, steganography is advantageous for its resilience to attacks by concealing the message in an innocent-looking cover signal. Minimal…
Contextual word representations generated by language models (LMs) learn spurious associations present in the training corpora. Recent findings reveal that adversaries can exploit these associations to reverse-engineer the private…
Jailbreak attacks pose a serious threat to Large Language Models (LLMs) by bypassing their safety mechanisms. A truly advanced jailbreak is defined not only by its effectiveness but, more critically, by its stealthiness. However, existing…