Related papers: Secure Seed-Based Multi-bit Watermarking for Diffu…
Putting a watermark into digital circuitry has its own set of challenges. Creating a secure watermark in printed matter usually involves including graphics that are difficult to reproduce. In circuitry, including additional circuitry that…
Modern generative diffusion models rely on vast training datasets, often including images with uncertain ownership or usage rights. Radioactive watermarks -- marks that transfer to a model's outputs -- can help detect when such unauthorized…
Algorithmic verification of realistic systems to satisfy safety and other temporal requirements has suffered from poor scalability of the employed formal approaches. To design systems with rigorous guarantees, many approaches still rely on…
Deepfakes pose significant security and privacy threats through malicious facial manipulations. While robust watermarking can aid in authenticity verification and source tracking, existing methods often lack the sufficient robustness…
LLMs now exhibit human-like skills in various fields, leading to worries about misuse. Thus, detecting generated text is crucial. However, passive detection methods are stuck in domain specificity and limited adversarial robustness. To…
Recent advances in generative AI have enabled the creation of highly realistic digital content, raising concerns around authenticity, ownership, and misuse. While watermarking has become an increasingly important mechanism to trace and…
In recent years, there has been significant advancement in the field of model watermarking techniques. However, the protection of image-processing neural networks remains a challenge, with only a limited number of methods being developed.…
Safeguarding the intellectual property of machine learning models has emerged as a pressing concern in AI security. Model watermarking is a powerful technique for protecting ownership of machine learning models, yet its reliability has been…
In the watermark detection scenario, also known as zero-bit watermarking, a watermark, carrying no hidden message, is inserted in content. The watermark detector checks for the presence of this particular weak signal in content. The article…
Latent generative models (e.g., Stable Diffusion) have become more and more popular, but concerns have arisen regarding potential misuse related to images generated by these models. It is, therefore, necessary to analyze the origin of…
This paper considers the problem of multi-bit generative watermarking for large language models under a worst-case false-alarm constraint. Prior work established a lower bound on the achievable miss-detection probability in the finite-token…
Multi-bit watermarking has emerged as a promising solution for embedding imperceptible binary messages into Large Language Model (LLM)-generated text, enabling reliable attribution and tracing of malicious usage of LLMs. Despite recent…
The advances in the Neural Radiance Fields (NeRF) research offer extensive applications in diverse domains, but protecting their copyrights has not yet been researched in depth. Recently, NeRF watermarking has been considered one of the…
In light of recent advancements in generative AI models, it has become essential to distinguish genuine content from AI-generated one to prevent the malicious usage of fake materials as authentic ones and vice versa. Various techniques have…
The rapid advancement of deep learning has turned models into highly valuable assets due to their reliance on massive data and costly training processes. However, these models are increasingly vulnerable to leakage and theft, highlighting…
Rapid advancements in multimodal large language models have enabled the creation of hyper-realistic images from textual descriptions. However, these advancements also raise significant concerns about unauthorized use, which hinders their…
In this paper, we introduce \emph{Luminark}, a training-free and probabilistically-certified watermarking method for general vision generative models. Our approach is built upon a novel watermark definition that leverages patch-level…
We show the viability of tackling misuses of large language models beyond the identification of machine-generated text. While existing zero-bit watermark methods focus on detection only, some malicious misuses demand tracing the adversary…
Ensuring robustness in image watermarking is crucial for and maintaining content integrity under diverse transformations. Recent self-supervised learning (SSL) approaches, such as DINO, have been leveraged for watermarking but primarily…
Digital watermarking is extensively used in ownership authentication and copyright protection. In this paper, we propose an efficient thresholding scheme to improve the watermark embedding procedure in an image. For the proposed algorithm,…