Related papers: Security analysis of a self-embedding fragile imag…
We study a basic question about cryptographic watermarking for generative models: how reliable can a watermark remain when an adversary is allowed to corrupt the encoded signal? To address this question, we introduce a minimal coding…
Watermarking techniques are vital for protecting intellectual property and preventing fraudulent use of media. Most previous watermarking schemes designed for diffusion models embed a secret key in the initial noise. The resulting pattern…
In recent years, steganography has emerged as one of the main research areas in information security. Least significant bit (LSB) steganography is one of the fundamental and conventional spatial domain methods, which is capable of hiding…
Rowhammer on GPU DRAM has enabled adversarial bit flips in model weights; shared KV-cache blocks in LLM serving systems present an analogous but previously unexamined target. In vLLM's Prefix Caching, these blocks exist as a single physical…
In today's digital landscape, the blending of AI-generated and authentic content has underscored the need for copyright protection and content authentication. Watermarking has become a vital tool to address these challenges, safeguarding…
Digital image watermarking has been widely used in different applications such as copyright protection of digital media, such as audio, image, and video files. Two opposing criteria of robustness and transparency are the goals of…
Recent advances in Large Language Models (LLMs) have raised urgent concerns about LLM-generated text authenticity, prompting regulatory demands for reliable identification mechanisms. Although watermarking offers a promising solution,…
Performance indicators characterizing modern steganographic techniques include capacity (i.e. the quantity of data that can be hidden in the cover medium), stego quality (i.e. artifacts visibility), security (i.e. undetectability), and…
In this paper, we propose a novel DNN watermarking method that utilizes a learnable image transformation method with a secret key. The proposed method embeds a watermark pattern in a model by using learnable transformed images and allows us…
Robust invisible watermarking embeds hidden information in images such that the watermark can survive various manipulations. However, the emergence of powerful diffusion-based image generation and editing techniques poses a new threat to…
As an essential technique for data privacy protection, reversible data hiding in encrypted images (RDHEI) methods have drawn intensive research interest in recent years. In response to the increasing demand for protecting data privacy,…
To hide a binary pattern in the palette image a steganographic scheme with blind detection is considered. The embedding algorithm uses the Lehmer code by palette color permutations for which the cover image palette is generally required.…
Fragile digital watermarking has been applied for authentication and alteration detection in images. Utilizing the cosine and Hartley transforms over finite fields, a new transform domain fragile watermarking scheme is introduced. A…
The most effective techniques to detect LLM-generated text rely on inserting a detectable signature -- or watermark -- during the model's decoding process. Most existing watermarking methods require access to the underlying LLM's logits,…
State-of-the-art text-to-image models generate photorealistic images at an unprecedented speed. This work focuses on models that operate in a bitwise autoregressive manner over a discrete set of tokens that is practically infinite in size.…
Embeddings as a Service (EaaS) is emerging as a crucial role in AI applications. Unfortunately, EaaS is vulnerable to model extraction attacks, highlighting the urgent need for copyright protection. Although some preliminary works propose…
Digital image watermarking is the process of embedding and extracting watermark covertly on a carrier image. Incorporating deep learning networks with image watermarking has attracted increasing attention during recent years. However,…
This paper proposes a strict authentication watermarking for medical images. In this scheme, we define region of interest (ROI) by taking the smallest rectangle around an image. The watermark is generated from hashing the area of interest.…
This paper presents a robust video watermarking scheme in Discrete Fourier Transform (DFT) and Sequencyordered Complex Hadamard Transform (SCHT). The DFT and SCHT coefficients are complex and consist of both magnitude and phase and are well…
A steganographic method based on the chaotic fractional map and in the DCT domain is proposed. This method embeds a secret message in some high frequency coefficients of the image using a 128-bit private key and a chaotic fractional map…