Backdoor attacks are an insidious security threat against machine learni...
Modern NLP models are often trained over large untrusted datasets, raisi...
Adversarial Transferability is an intriguing property of adversarial exa...
Convolutional neural network (CNN) models for computer vision are powerf...
We study how to communicate findings of Bayesian inference to third part...
Differential privacy formalises privacy-preserving mechanisms that provi...