40 citations · 100 across the 14 of their papers we have counts for
17 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…
Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models
Guillermo Ortiz-Jimenez, Alessandro Favero, Pascal Frossard
Task arithmetic has recently emerged as a cost-effective and scalable approach to edit pre-trained models directly in weight space: By adding the fine-tuned weights of different ta…
When does Privileged Information Explain Away Label Noise?
Guillermo Ortiz-Jimenez, Mark Collier, Anant Nawalgaria +4
Leveraging privileged information (PI), or features available during training but not at test time, has recently been shown to be an effective method for addressing label noise. Ho…
Catastrophic overfitting can be induced with discriminative non-robust features
Guillermo Ortiz-Jiménez, Pau de Jorge, Amartya Sanyal +5
Adversarial training (AT) is the de facto method for building robust neural networks, but it can be computationally expensive. To mitigate this, fast single-step attacks can be use…
On the benefits of knowledge distillation for adversarial robustness
Javier Maroto, Guillermo Ortiz-Jiménez, Pascal Frossard
Knowledge distillation is normally used to compress a big network, or teacher, onto a smaller one, the student, by training it to match its outputs. Recently, some works have shown…
PRIME: A few primitives can boost robustness to common corruptions
Apostolos Modas, Rahul Rade, Guillermo Ortiz-Jiménez +2
Despite their impressive performance on image classification tasks, deep networks have a hard time generalizing to unforeseen corruptions of their data. To fix this vulnerability,…
A Structured Dictionary Perspective on Implicit Neural Representations
Gizem Yüce, Guillermo Ortiz-Jiménez, Beril Besbinar +1
Implicit neural representations (INRs) have recently emerged as a promising alternative to classical discretized representations of signals. Nevertheless, despite their practical s…
What can linearized neural networks actually say about generalization?
Guillermo Ortiz-Jiménez, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard
For certain infinitely-wide neural networks, the neural tangent kernel (NTK) theory fully characterizes generalization, but for the networks used in practice, the empirical NTK onl…
A neural anisotropic view of underspecification in deep learning
Guillermo Ortiz-Jimenez, Itamar Franco Salazar-Reque, Apostolos Modas +2
The underspecification of most machine learning pipelines means that we cannot rely solely on validation performance to assess the robustness of deep learning systems to naturally…
Optimism in the Face of Adversity: Understanding and Improving Deep Learning through Adversarial Robustness
Guillermo Ortiz-Jimenez, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli +1
Driven by massive amounts of data and important advances in computational resources, new deep learning systems have achieved outstanding results in a large spectrum of applications…
Neural Anisotropy Directions
Guillermo Ortiz-Jimenez, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli +1
In this work, we analyze the role of the network architecture in shaping the inductive bias of deep classifiers. To that end, we start by focusing on a very simple problem, i.e., c…
Hold me tight! Influence of discriminative features on deep network boundaries
Guillermo Ortiz-Jimenez, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli +1
Important insights towards the explainability of neural networks reside in the characteristics of their decision boundaries. In this work, we borrow tools from the field of adversa…
On the choice of graph neural network architectures
Clément Vignac, Guillermo Ortiz-Jiménez, Pascal Frossard
Seminal works on graph neural networks have primarily targeted semi-supervised node classification problems with few observed labels and high-dimensional signals. With the developm…
Forward-Backward Splitting for Optimal Transport based Problems
Guillermo Ortiz-Jimenez, Mireille El Gheche, Effrosyni Simou +2
Optimal transport aims to estimate a transportation plan that minimizes a displacement cost. This is realized by optimizing the scalar product between the sought plan and the given…
Sampling and Reconstruction of Signals on Product Graphs
Guillermo Ortiz-Jiménez, Mario Coutino, Sundeep Prabhakar Chepuri +1
In this paper, we consider the problem of subsampling and reconstruction of signals that reside on the vertices of a product graph, such as sensor network time series, genomic sign…
Sparse Sampling for Inverse Problems with Tensors
Guillermo Ortiz-Jiménez, Mario Coutino, Sundeep Prabhakar Chepuri +1
We consider the problem of designing sparse sampling strategies for multidomain signals, which can be represented using tensors that admit a known multilinear decomposition. We lev…