Despite their demonstrated utility for NLP, multimodal counterfactual examples have been relatively unexplored due to the difficulty of creating paired image-text data with minimal counterfactual changes. To address this challenge, we introduce a scalable framework for automatic generation of counterfactual examples using text-to-image diffusion models.

We consider the problem of discretization of neural operators between Hilbert spaces in a general framework including skip connections. We focus on bijec-tive neural operators through the lens of diffeomorphisms in infinite dimensions.

Project lead, main contributor, correspondence to alexandre.rame@isir.upmc.fr. Equal experimental contribution, order determined at random. Further information and resources related to this project can be found on this website.

In a backdoor attack, an adversary injects corrupted data into a model's training dataset in order to gain control over its predictions on images with a specific attacker-defined trigger. A typical corrupted training example requires altering both the image, by applying the trigger, and the label. Models trained on clean images, therefore, were considered safe from backdoor attacks. However, in some common machine learning scenarios, the training labels are provided by potentially malicious third-parties. This includes crowd-sourced annotation and knowledge distillation. We, hence, investigate a fundamental question: can we launch a successful backdoor attack by only corrupting labels?

Figure 1: R-Blur adds Gaussian noise to image (a) with the fixation point (red dot) to obtain (b).

Until now, no tabular method has consistently outperformed classical supervised learning, which ignores these shifts.

Transformers learn to approximate second-order optimization methods for ICL.