62 citations · 101 across the 4 of their papers we have counts for
5 papers
Probability Calibration for Knowledge Graph Embedding Models
Pedro Tabacof, Luca Costabello
Knowledge graph embedding research has overlooked the problem of probability calibration. We show popular embedding models are indeed uncalibrated. That means probability estimates…
Adversarial Attacks on Variational Autoencoders
George Gondim-Ribeiro, Pedro Tabacof, Eduardo Valle
Adversarial attacks are malicious inputs that derail machine-learning models. We propose a scheme to attack autoencoders, as well as a quantitative evaluation framework that correl…
Known Unknowns: Uncertainty Quality in Bayesian Neural Networks
Ramon Oliveira, Pedro Tabacof, Eduardo Valle
We evaluate the uncertainty quality in neural networks using anomaly detection. We extract uncertainty measures (e.g. entropy) from the predictions of candidate models, use those m…
Adversarial Images for Variational Autoencoders
Pedro Tabacof, Julia Tavares, Eduardo Valle
We investigate adversarial attacks for autoencoders. We propose a procedure that distorts the input image to mislead the autoencoder in reconstructing a completely different target…
Exploring the Space of Adversarial Images
Pedro Tabacof, Eduardo Valle
Adversarial examples have raised questions regarding the robustness and security of deep neural networks. In this work we formalize the problem of adversarial images given a pretra…