Related papers: A watermarking algorithm satisfying topological ch…
The advancement of Large Language Models (LLMs) has led to increasing concerns about the misuse of AI-generated text, and watermarking for LLM-generated text has emerged as a potential solution. However, it is challenging to generate…
As artificial intelligence surpasses human capabilities in text generation, the necessity to authenticate the origins of AI-generated content has become paramount. Unbiased watermarks offer a powerful solution by embedding statistical…
We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches. We present a way to embed both marks and binary messages into their latent spaces, leveraging data augmentation at marking…
Watermarking has emerged as an effective solution for copyright protection of synthetic data. However, applying watermarking techniques to synthetic tabular data presents challenges, as tabular data can easily lose their watermarks through…
We consider the emerging problem of identifying the presence and use of watermarking schemes in widely used, publicly hosted, closed source large language models (LLMs). We introduce a suite of baseline algorithms for identifying watermarks…
From network topologies to online social networks, many of today's most sensitive datasets are captured in large graphs. A significant challenge facing owners of these datasets is how to share sensitive graphs with collaborators and…
Speech watermarking techniques can proactively mitigate the potential harmful consequences of instant voice cloning techniques. These techniques involve the insertion of signals into speech that are imperceptible to humans but can be…
This research work presents a new class of non-blind information hiding algorithms that are stego-secure and robust. They are based on some finite domains iterations having the Devaney's topological chaos property. Thanks to a complete…
Security of information has become a major issue during the last decades. New algorithms based on chaotic maps were suggested for protection of different types of multimedia data, especially digital images and videos in this period.…
Topological features in quantum computing provide controllability and noise error avoidance in the performance of logical gates. While such resilience is favored in the manipulation of quantum systems, it is very hard to identify…
Chaos and its applications in the field of secure communications have attracted a lot of attention. Chaos-based pseudo-random number generators are critical to guarantee security over open networks as the Internet. We have previously…
The advancement of secure communication and identity verification fields has significantly increased through the use of deep learning techniques for data hiding. By embedding information into a noise-tolerant signal such as audio, video, or…
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,…
Deep learning has achieved tremendous success in numerous industrial applications. As training a good model often needs massive high-quality data and computation resources, the learned models often have significant business values. However,…
This paper presents an application of statistical machine learning to the field of watermarking. We propose a new attack model on additive spread-spectrum watermarking systems. The proposed attack is based on Bayesian statistics. We…
Recent progress toward classifying low-dimensional chaos measured from time series data is described. This classification theory assigns a template to the time series once the time series is embedded in three dimensions. The template…
The problem of Turing pattern formation has attracted much attention in nonlinear science as well as physics, chemistry and biology. So far all Turing patterns have been observed in stationary and oscillatory media only. In this letter we…
Active techniques have been introduced to give better detectability performance for cyber-attack diagnosis in cyber-physical systems (CPS). In this paper, switching multiplicative watermarking is considered, whereby we propose an optimal…
Deterministic chaos permits a precise notion of a "perfect measurement" as one that, when obtained repeatedly, captures all of the information created by the system's evolution with minimal redundancy. Finding an optimal measurement is…
Embedding watermarks into the output of generative models is essential for establishing copyright and verifiable ownership over the generated content. Emerging diffusion model watermarking methods either embed watermarks in the frequency…