29 citations · 40 across the 13 of their papers we have counts for
15 papers
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…
We Can Hide More Bits: The Unused Watermarking Capacity in Theory and in Practice
Aleksandar Petrov, Pierre Fernandez, Tomáš Souček +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…
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…
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…
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…
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…
Near to Mid-term Risks and Opportunities of Open-Source Generative AI
Francisco Eiras, Aleksandar Petrov, Bertie Vidgen +21
In the next few years, applications of Generative AI are expected to revolutionize a number of different areas, ranging from science & medicine to education. The potential for thes…
Prompting a Pretrained Transformer Can Be a Universal Approximator
Aleksandar Petrov, Philip H. S. Torr, Adel Bibi
Despite the widespread adoption of prompting, prompt tuning and prefix-tuning of transformer models, our theoretical understanding of these fine-tuning methods remains limited. A k…
When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
Aleksandar Petrov, Philip H. S. Torr, Adel Bibi
Context-based fine-tuning methods, including prompting, in-context learning, soft prompting (also known as prompt tuning), and prefix-tuning, have gained popularity due to their ab…
Language Model Tokenizers Introduce Unfairness Between Languages
Aleksandar Petrov, Emanuele La Malfa, Philip H. S. Torr +1
Recent language models have shown impressive multilingual performance, even when not explicitly trained for it. Despite this, there are concerns about the quality of their outputs…
Certifying Ensembles: A General Certification Theory with S-Lipschitzness
Aleksandar Petrov, Francisco Eiras, Amartya Sanyal +2
Improving and guaranteeing the robustness of deep learning models has been a topic of intense research. Ensembling, which combines several classifiers to provide a better model, ha…
HiddenGems: Efficient safety boundary detection with active learning
Aleksandar Petrov, Carter Fang, Khang Minh Pham +3
Evaluating safety performance in a resource-efficient way is crucial for the development of autonomous systems. Simulation of parameterized scenarios is a popular testing strategy…
Robustness of Unsupervised Representation Learning without Labels
Aleksandar Petrov, Marta Kwiatkowska
Unsupervised representation learning leverages large unlabeled datasets and is competitive with supervised learning. But non-robust encoders may affect downstream task robustness.…
Integrated Benchmarking and Design for Reproducible and Accessible Evaluation of Robotic Agents
Jacopo Tani, Andrea F. Daniele, Gianmarco Bernasconi +10
As robotics matures and increases in complexity, it is more necessary than ever that robot autonomy research be reproducible. Compared to other sciences, there are specific challen…
Learning Camera Miscalibration Detection
Andrei Cramariuc, Aleksandar Petrov, Rohit Suri +3
Self-diagnosis and self-repair are some of the key challenges in deploying robotic platforms for long-term real-world applications. One of the issues that can occur to a robot is m…