1k citations · 2.2k across the 34 of their papers we have counts for
35 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…
On the Difficulty of Constructing a Robust and Publicly-Detectable Watermark
Jaiden Fairoze, Guillermo Ortiz-Jimenez, Mel Vecerik +2
This work investigates the theoretical boundaries of creating publicly-detectable schemes to enable the provenance of watermarked imagery. Metadata-based approaches like C2PA provi…
Evaluating Model Bias Requires Characterizing its Mistakes
Isabela Albuquerque, Jessica Schrouff, David Warde-Farley +3
The ability to properly benchmark model performance in the face of spurious correlations is important to both build better predictors and increase confidence that models are operat…
Generative models improve fairness of medical classifiers under distribution shifts
Ira Ktena, Olivia Wiles, Isabela Albuquerque +9
A ubiquitous challenge in machine learning is the problem of domain generalisation. This can exacerbate bias against groups or labels that are underrepresented in the datasets used…
Differentially Private Diffusion Models Generate Useful Synthetic Images
Sahra Ghalebikesabi, Leonard Berrada, Sven Gowal +7
The ability to generate privacy-preserving synthetic versions of sensitive image datasets could unlock numerous ML applications currently constrained by data availability. Due to t…
Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts
Francesco Croce, Sylvestre-Alvise Rebuffi, Evan Shelhamer +1
Adversarial training is widely used to make classifiers robust to a specific threat or adversary, such as -norm bounded perturbations of a given -norm. However, existing…
Benchmarking Robustness to Adversarial Image Obfuscations
Florian Stimberg, Ayan Chakrabarti, Chun-Ta Lu +9
Automated content filtering and moderation is an important tool that allows online platforms to build striving user communities that facilitate cooperation and prevent abuse. Unfor…
Hindering Adversarial Attacks with Implicit Neural Representations
Andrei A. Rusu, Dan A. Calian, Sven Gowal +1
We introduce the Lossy Implicit Network Activation Coding (LINAC) defence, an input transformation which successfully hinders several common adversarial attacks on CIFAR- class…
Revisiting adapters with adversarial training
Sylvestre-Alvise Rebuffi, Francesco Croce, Sven Gowal
While adversarial training is generally used as a defense mechanism, recent works show that it can also act as a regularizer. By co-training a neural network on clean and adversari…
Discovering Bugs in Vision Models using Off-the-shelf Image Generation and Captioning
Olivia Wiles, Isabela Albuquerque, Sven Gowal
Automatically discovering failures in vision models under real-world settings remains an open challenge. This work demonstrates how off-the-shelf, large-scale, image-to-text and te…
Robustness of Epinets against Distributional Shifts
Xiuyuan Lu, Ian Osband, Seyed Mohammad Asghari +4
Recent work introduced the epinet as a new approach to uncertainty modeling in deep learning. An epinet is a small neural network added to traditional neural networks, which, toget…
Competition-Level Code Generation with AlphaCode
Yujia Li, David Choi, Junyoung Chung +23
Programming is a powerful and ubiquitous problem-solving tool. Developing systems that can assist programmers or even generate programs independently could make programming more pr…
Evaluating the Adversarial Robustness of Adaptive Test-time Defenses
Francesco Croce, Sven Gowal, Thomas Brunner +3
Adaptive defenses, which optimize at test time, promise to improve adversarial robustness. We categorize such adaptive test-time defenses, explain their potential benefits and draw…
A Fine-Grained Analysis on Distribution Shift
Olivia Wiles, Sven Gowal, Florian Stimberg +4
Robustness to distribution shifts is critical for deploying machine learning models in the real world. Despite this necessity, there has been little work in defining the underlying…
Data Augmentation Can Improve Robustness
Sylvestre-Alvise Rebuffi, Sven Gowal, Dan A. Calian +3
Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training. In this paper, we focus on reducing robust ove…
An Empirical Investigation of Learning from Biased Toxicity Labels
Neel Nanda, Jonathan Uesato, Sven Gowal
Collecting annotations from human raters often results in a trade-off between the quantity of labels one wishes to gather and the quality of these labels. As such, it is often only…
Improving Robustness using Generated Data
Sven Gowal, Sylvestre-Alvise Rebuffi, Olivia Wiles +3
Recent work argues that robust training requires substantially larger datasets than those required for standard classification. On CIFAR-10 and CIFAR-100, this translates into a si…
A Closer Look at the Adversarial Robustness of Information Bottleneck Models
Iryna Korshunova, David Stutz, Alexander A. Alemi +2
We study the adversarial robustness of information bottleneck models for classification. Previous works showed that the robustness of models trained with information bottlenecks ca…
Defending Against Image Corruptions Through Adversarial Augmentations
Dan A. Calian, Florian Stimberg, Olivia Wiles +4
Modern neural networks excel at image classification, yet they remain vulnerable to common image corruptions such as blur, speckle noise or fog. Recent methods that focus on this p…
Fixing Data Augmentation to Improve Adversarial Robustness
Sylvestre-Alvise Rebuffi, Sven Gowal, Dan A. Calian +3
Adversarial training suffers from robust overfitting, a phenomenon where the robust test accuracy starts to decrease during training. In this paper, we focus on both heuristics-dri…
Make Sure You're Unsure: A Framework for Verifying Probabilistic Specifications
Leonard Berrada, Sumanth Dathathri, Krishnamurthy Dvijotham +5
Most real world applications require dealing with stochasticity like sensor noise or predictive uncertainty, where formal specifications of desired behavior are inherently probabil…
Autoencoding Variational Autoencoder
A. Taylan Cemgil, Sumedh Ghaisas, Krishnamurthy Dvijotham +2
Does a Variational AutoEncoder (VAE) consistently encode typical samples generated from its decoder? This paper shows that the perhaps surprising answer to this question is `No'; a…
Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples
Sven Gowal, Chongli Qin, Jonathan Uesato +2
Adversarial training and its variants have become de facto standards for learning robust deep neural networks. In this paper, we explore the landscape around adversarial training i…
An empirical investigation of the challenges of real-world reinforcement learning
Gabriel Dulac-Arnold, Nir Levine, Daniel J. Mankowitz +4
Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is beginning to show some successes in real-world scenarios. However, much of the research a…