Related papers: Robust Steganography from Large Language Models

Covert communication (also known as steganography) is the practice of concealing a secret inside an innocuous-looking public object (cover) so that the modified public object (covert code) makes sense to everyone but only someone who knows…

In the face of escalating surveillance and censorship within the cyberspace, the sanctity of personal privacy has come under siege, necessitating the development of steganography, which offers a way to securely hide messages within…

Linguistic steganography embeds secret information into seemingly innocuous text to safeguard privacy under surveillance. Generative linguistic steganography leverages the probability distributions of language models (LMs) and applies…

Conventional covert image communication is assumed to transmit the message, in the securest way possible for a given payload, over lossless channels, and the associated steganographic schemes are generally vulnerable to active attacks,…

Despite remarkable progress in steganography, embedding semantically rich, sentence-level information into carriers remains a challenging problem. In this work, we present a novel concept of Semantic Steganography, which aims to hide…

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…

Linguistic steganography enables covert communication through embedding secret messages into innocuous texts; however, current methods face critical limitations in payload capacity and security. Traditional modification-based methods…

Monitoring Large Language Model (LLM) outputs is crucial for mitigating risks from misuse and misalignment. However, LLMs could evade monitoring through steganography: Encoding hidden information within seemingly benign generations. In this…

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…

Language Models (LMs) emit Chains-of-Thought (CoTs) that drive much of their capability. However, the same sequence that carries useful reasoning can also covertly convey messages: a misaligned model may embed covert information in its CoT…

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…

Steganography is a technique for covert communication between two parties. With the rapid development of deep neural networks (DNN), more and more steganographic networks are proposed recently, which are shown to be promising to achieve…

Steganography conceals the secret message into the cover media, generating a stego media which can be transmitted on public channels without drawing suspicion. As its countermeasure, steganalysis mainly aims to detect whether the secret…

The security of private communication is increasingly at risk due to widespread surveillance. Steganography, a technique for embedding secret messages within innocuous carriers, enables covert communication over monitored channels. Provably…

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…

In the ever-expanding digital landscape, safeguarding sensitive information remains paramount. This paper delves deep into digital protection, specifically focusing on steganography. While prior research predominantly fixated on individual…

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…

State of the art generative models of human-produced content are the focus of many recent papers that explore their use for steganographic communication. In particular, generative models of natural language text. Loosely, these works…

Steganography is an information hiding technique for covert communication. The core issue in steganography design is the rate-distortion coding problem. Polar codes, which have been proven to achieve the rate-distortion bound for any binary…

For as long as humans have participated in the act of communication, concealing information in those communicative mediums has manifested into an art of its own. Crytographic messages, through written language or images, are a means of…