Related papers: Robust Steganography from Large Language Models

Having a clean dataset has been the foundational assumption of most natural language processing (NLP) systems. However, properly written text is rarely found in real-world scenarios and hence, oftentimes invalidates the aforementioned…

Steganography is an information hiding application which aims to hide secret data imperceptibly into a commonly used media. Unfortunately, the theoretical hiding asymptotical capacity of steganographic systems is not attained by algorithms…

Steganography, or hiding messages in plain sight, is a form of information hiding that is most commonly used for covert communication. As modern steganographic mediums include images, text, audio, and video, this communication method is…

Image steganography is the art of concealing secret information in images in a way that is imperceptible to unauthorized parties. Recent advances show that is possible to use a fixed neural network (FNN) for secret embedding and extraction.…

Traditional video steganography methods are based on modifying the covert space for embedding, whereas we propose an innovative approach that embeds secret message within semantic feature for steganography during the video editing process.…

Improving the safety and reliability of large language models (LLMs) is a crucial aspect of realizing trustworthy AI systems. Although alignment methods aim to suppress harmful content generation, LLMs are often still vulnerable to…

Large language models (LLMs) are susceptible to social-engineered attacks that are human-interpretable but require a high level of comprehension for LLMs to counteract. Existing defensive measures can only mitigate less than half of these…

Steganography is collection of methods to hide secret information ("payload") within non-secret information "container"). Its counterpart, Steganalysis, is the practice of determining if a message contains a hidden payload, and recovering…

Recent developments in Large Language Models (LLMs) have manifested significant advancements. To facilitate safeguards against malicious exploitation, a body of research has concentrated on aligning LLMs with human preferences and…

Image steganography is the technique of embedding secret information within images. The development of deep learning has led to significant advances in this field. However, existing methods often struggle to balance image quality, embedding…

Large Language Models (LLMs) have advanced various Natural Language Processing (NLP) tasks, such as text generation and translation, among others. However, these models often generate texts that can perpetuate biases. Existing approaches to…

Aligned large language models (LLMs) are vulnerable to jailbreaking attacks, which bypass the safeguards of targeted LLMs and fool them into generating objectionable content. While initial defenses show promise against token-based threat…

We propose an approach for preventing unsafe or otherwise low-quality large language model (LLM) outputs by leveraging the stochasticity of LLMs, an approach we call Repeated Checking with Regeneration (RCR). In this system, LLM checkers…

Despite efforts to align large language models (LLMs) with human intentions, widely-used LLMs such as GPT, Llama, and Claude are susceptible to jailbreaking attacks, wherein an adversary fools a targeted LLM into generating objectionable…

Visual Language Models (VLMs) have achieved remarkable progress, yet their reliability under small, meaning-preserving input changes remains poorly understood. We present the first large-scale, systematic study of VLM robustness to benign…

Large Language Models (LLMs) have achieved tremendous success in various tasks, yet concerns about their safety and security have emerged. In particular, they pose risks of generating harmful content and are vulnerable to jailbreaking…

Steganography and Cryptography are two popular ways of sending vital information in a secret way. One hides the existence of the message and the other distorts the message itself. There are many cryptography techniques available; among them…

Recent work (Baluja, 2017) showed that using a pair of deep encoders and decoders, embedding a full-size secret image into a container image of the same size is achieved. This method distributes the information of the secret image across…

We provide a new provably-secure steganographic encryption protocol that is proven secure in the complexity-theoretic framework of Hopper et al. The fundamental building block of our steganographic encryption protocol is a "one-time…

Large language model (LLM) watermarking has shown promise in detecting AI-generated content and mitigating misuse, with prior work claiming robustness against paraphrasing and text editing. In this paper, we argue that existing evaluations…