7 papers
We Can Hide More Bits: The Unused Watermarking Capacity in Theory and in Practice
Aleksandar Petrov, Pierre Fernandez, Tomáš SouÄek +1
Despite rapid progress in deep learning-based image watermarking, the capacity of current robust methods remains limited to the scale of only a few hundred bits. Such plateauing pr…
SynthID-Image: Image watermarking at internet scale
Sven Gowal, Rudy Bunel, Florian Stimberg +23
We introduce SynthID-Image, a deep learning-based system for invisibly watermarking AI-generated imagery. This paper documents the technical desiderata, threat models, and practica…
Long Context In-Context Compression by Getting to the Gist of Gisting
Aleksandar Petrov, Mark Sandler, Andrey Zhmoginov +2
Long context processing is critical for the adoption of LLMs, but existing methods often introduce architectural complexity that hinders their practical adoption. Gisting, an in-co…
Do as I do (Safely): Mitigating Task-Specific Fine-tuning Risks in Large Language Models
Francisco Eiras, Aleksandar Petrov, Philip H. S. Torr +2
Recent research shows that fine-tuning on benign instruction-following data can inadvertently undo the safety alignment process and increase a model's propensity to comply with har…
On the Coexistence and Ensembling of Watermarks
Aleksandar Petrov, Shruti Agarwal, Philip H. S. Torr +2
Watermarking, the practice of embedding imperceptible information into media such as images, videos, audio, and text, is essential for intellectual property protection, content pro…
Universal In-Context Approximation By Prompting Fully Recurrent Models
Aleksandar Petrov, Tom A. Lamb, Alasdair Paren +2
Zero-shot and in-context learning enable solving tasks without model fine-tuning, making them essential for developing generative model solutions. Therefore, it is crucial to under…