Related papers: FoldMark: Protecting Protein Generative Models wit…
Diffusion models (DMs) have demonstrated advantageous potential on generative tasks. Widespread interest exists in incorporating DMs into downstream applications, such as producing or editing photorealistic images. However, practical…
Large Language Models (LLMs) are increasingly integrated into diverse industries, posing substantial security risks due to unauthorized replication and misuse. To mitigate these concerns, robust identification mechanisms are widely…
Proteins perform critical processes in all living systems: converting solar energy into chemical energy, replicating DNA, as the basis of highly performant materials, sensing and much more. While an incredible range of functionality has…
A reliable prediction of 3D protein structures from sequence data remains a big challenge due to both theoretical and computational difficulties. We have previously shown that our kinetostatic compliance method (KCM) implemented into the…
Watermarking has been widely adopted for protecting the intellectual property (IP) of Deep Neural Networks (DNN) to defend the unauthorized distribution. Unfortunately, the popular data-poisoning DNN watermarking scheme relies on target…
Generative models can generate photorealistic images at scale. This raises urgent concerns about the ability to detect synthetically generated images and attribute these images to specific sources. While watermarking has emerged as a…
Watermarking is a commonly used strategy to protect creators' rights to digital images, videos and audio. Recently, watermarking methods have been extended to deep learning models -- in principle, the watermark should be preserved when an…
Generative AI models pose a significant challenge to intellectual property (IP), as they can replicate unique artistic styles and concepts without attribution. While watermarking offers a potential solution, existing methods often fail in…
Invisible watermarks safeguard images' copyrights by embedding hidden messages only detectable by owners. They also prevent people from misusing images, especially those generated by AI models. We propose a family of regeneration attacks to…
Text watermarking for large language models (LLMs) enables model owners to verify text origin and protect intellectual property. While watermarking methods for closed-source LLMs are relatively mature, extending them to open-source models…
3D models, particularly AI-generated ones, have witnessed a recent surge across various industries such as entertainment. Hence, there is an alarming need to protect the intellectual property and avoid the misuse of these valuable assets.…
Artificial Intelligence Generated Content (AIGC), particularly video generation with diffusion models, has been advanced rapidly. Invisible watermarking is a key technology for protecting AI-generated videos and tracing harmful content, and…
The vast amounts of digital content captured from the real world or AI-generated media necessitate methods for copyright protection, traceability, or data provenance verification. Digital watermarking serves as a crucial approach to address…
Data watermarking in language models injects traceable signals, such as specific token sequences or stylistic patterns, into copyrighted text, allowing copyright holders to track and verify training data ownership. Previous data…
We develop a multi-scale approach to simulate hydrated nanobio systems under realistic condi- tions (e.g., nanoparticles and protein solutions at physiological conditions over time-scales up to hours). We combine atomistic simulations of…
Model watermarking techniques can embed watermark information into the protected model for ownership declaration by constructing specific input-output pairs. However, existing watermarks are easily removed when facing model stealing…
The current work is focusing on the implementation of a robust watermarking algorithm for digital images, which is based on an innovative spread spectrum analysis algorithm for watermark embedding and on a content-based image retrieval…
Inverse protein folding, the process of designing sequences that fold into a specific 3D structure, is crucial in bio-engineering and drug discovery. Traditional methods rely on experimentally resolved structures, but these cover only a…
Motivated by the problem of detecting AI-generated text, we consider the problem of watermarking the output of language models with provable guarantees. We aim for watermarks which satisfy: (a) undetectability, a cryptographic notion…
Watermarking embeds imperceptible patterns into images for authenticity verification. However, existing methods often lack robustness against various transformations primarily including distortions, image regeneration, and adversarial…