Related papers: Latent-Mark: An Audio Watermark Robust to Neural R…
DNN-based watermarking methods are rapidly developing and delivering impressive performances. Recent advances achieve resolution-agnostic image watermarking by reducing the variant resolution watermarking problem to a fixed resolution…
Deep neural networks (DNNs) have achieved significant success in real-world applications. However, safeguarding their intellectual property (IP) remains extremely challenging. Existing DNN watermarking for IP protection often require…
AI watermarking embeds invisible signals within images to provide provenance information and identify content as AI-generated. In this paper, we introduce MarkSweep, a novel watermark removal attack that effectively erases the embedded…
Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable to structural perturbations, such as sentence splitting and…
Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to humans but algorithmically detectable from a short span of tokens. We propose a…
EEG-based neural networks, pivotal in medical diagnosis and brain-computer interfaces, face significant intellectual property (IP) risks due to their reliance on sensitive neurophysiological data and resource-intensive development. Current…
The intellectual property (IP) of Deep neural networks (DNNs) can be easily ``stolen'' by surrogate model attack. There has been significant progress in solutions to protect the IP of DNN models in classification tasks. However, little…
As a self-supervised learning paradigm, contrastive learning has been widely used to pre-train a powerful encoder as an effective feature extractor for various downstream tasks. This process requires numerous unlabeled training data and…
Large language models (LLMs) have show great ability in various natural language tasks. However, there are concerns that LLMs are possible to be used improperly or even illegally. To prevent the malicious usage of LLMs, detecting…
With the growth of editing and sharing images through the internet, the importance of protecting the images' authorship has increased. Robust watermarking is a known approach to maintaining copyright protection. Robustness and…
Recent progress in large language models enables the creation of realistic machine-generated content. Watermarking is a promising approach to distinguish machine-generated text from human text, embedding statistical signals in the output…
Large Language Models (LLMs) can be misused to spread unwanted content at scale. Content watermarking deters misuse by hiding messages in content, enabling its detection using a secret watermarking key. Robustness is a core security…
Latent-based diffusion model watermarking embeds watermarks into generated images' latent space to enable content attribution, offering a training-free solution for intellectual property protection and digital forensics. However, these…
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…
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.…
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 LLM-generated text is critical for content attribution and misinformation prevention. However, existing methods compromise text quality, require white-box model access and logit manipulation. These limitations exclude API-based…
Watermarking is a crucial tool for safeguarding copyrights and can serve as a more aesthetically pleasing alternative to QR codes. In recent years, watermarking methods based on deep learning have proved superior robustness against complex…
Recent advances in Text-To-Speech (TTS) technology have enabled synthetic speech to mimic human voices with remarkable realism, raising significant security concerns. This underscores the need for traceable TTS models-systems capable of…
The widespread adoption of large language models (LLMs) necessitates reliable methods to detect LLM-generated text. We introduce SimMark, a robust sentence-level watermarking algorithm that makes LLMs' outputs traceable without requiring…