Related papers: ReTokSync: Self-Synchronizing Tokenization Disambi…
Recent research in provably secure neural linguistic steganography has overlooked a crucial aspect: the sender must detokenize stegotexts to avoid raising suspicion from the eavesdropper. The segmentation ambiguity problem, which arises…
Recent steganographic schemes, starting with Meteor (CCS'21), rely on leveraging large language models (LLMs) to resolve a historically-challenging task of disguising covert communication as ``innocent-looking'' natural-language…
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…
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…
Linguistic steganography (LS) conceals the presence of communication by embedding secret information into a text. How to generate a high-quality text carrying secret information is a key problem. With the widespread application of deep…
Neural linguistic steganography aims to embed information into natural text while preserving statistical undetectability. A fundamental challenge in this ffeld stems from tokenization ambiguity in modern tokenizers, which can lead to…
In the era of Large Language Models (LLMs), generative linguistic steganography has become a prevalent technique for hiding information within model-generated texts. However, traditional steganography methods struggle to effectively align…
Robust steganography is a technique of hiding secret messages in images so that the message can be recovered after additional image processing. One of the most popular processing operations is JPEG recompression. Unfortunately, most of…
We introduce Representation Tokenizer (RepTok), a generative modeling framework that represents an image using a single continuous latent token obtained from self-supervised vision transformers. Building on a pre-trained SSL encoder, we…
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…
Existing state-of-the-art image tokenization methods leverage diverse semantic features from pre-trained vision models for additional supervision, to expand the distribution of latent representations and thereby improve the quality of image…
Despite their fundamental role, it remains unclear what properties could make tokenizers more effective for generative modeling. We observe that modern generative models share a conceptually similar training objective -- reconstructing…
Generating an image from a given text description has two goals: visual realism and semantic consistency. Although significant progress has been made in generating high-quality and visually realistic images using generative adversarial…
Generative linguistic steganography mainly utilized language models and applied steganographic sampling (stegosampling) to generate high-security steganographic text (stegotext). However, previous methods generally lead to statistical…
Modern Text-to-Speech (TTS) systems increasingly leverage Large Language Model (LLM) architectures to achieve scalable, high-fidelity, zero-shot generation. However, these systems typically rely on fixed-frame-rate acoustic tokenization,…
In this work, we propose "global style tokens" (GSTs), a bank of embeddings that are jointly trained within Tacotron, a state-of-the-art end-to-end speech synthesis system. The embeddings are trained with no explicit labels, yet learn to…
We examine the speech modeling potential of generative spoken language modeling (GSLM), which involves using learned symbols derived from data rather than phonemes for speech analysis and synthesis. Since GSLM facilitates textless spoken…
This thesis addresses automatic lexical error recovery and tokenization of corrupt text input. We propose a technique that can automatically correct misspellings, segmentation errors and real-word errors in a unified framework that uses…
In autoregressive (AR) image generation, visual tokenizers compress images into compact discrete latent tokens, enabling efficient training of downstream autoregressive models for visual generation via next-token prediction. While scaling…
The black-box nature of end-to-end speech translation (E2E ST) systems makes it difficult to understand how source language inputs are being mapped to the target language. To solve this problem, we would like to simultaneously generate…