7 papers
Provably Secure Steganography Based on List Decoding
Kaiyi Pang, Minhao Bai
Steganography embeds secret messages in seemingly innocuous carriers for covert communication under surveillance. Current Provably Secure Steganography (PSS) schemes based on langu…
DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models
Xiaoxiao He, Quan Dao, Ligong Han +14
Discrete diffusion models have achieved success in tasks like image generation and masked language modeling but face limitations in controlled content editing. We introduce DICE (D…
ModelShield: Adaptive and Robust Watermark against Model Extraction Attack
Kaiyi Pang, Tao Qi, Chuhan Wu +3
Large language models (LLMs) demonstrate general intelligence across a variety of machine learning tasks, thereby enhancing the commercial value of their intellectual property (IP)…
Shifting-Merging: Secure, High-Capacity and Efficient Steganography via Large Language Models
Minhao Bai, Jinshuai Yang, Kaiyi Pang +2
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,…
Let Watermarks Speak: A Robust and Unforgeable Watermark for Language Models
Minhao Bai
Watermarking is an effective way to trace model-generated content. Current watermark methods cannot resist forgery attacks, such as a deceptive claim that the model-generated conte…
Semantic Steganography: A Framework for Robust and High-Capacity Information Hiding using Large Language Models
Minhao Bai, Jinshuai Yang, Kaiyi Pang +2
In the era of Large Language Models (LLMs), generative linguistic steganography has become a prevalent technique for hiding information within model-generated texts. However, tradi…