The trustworthiness of machine learning has emerged as a critical topic in the field,
encompassing various applications and research areas such as robustness, security …

Concerns about the societal impact of AI-based services and systems has encouraged
governments and other organisations around the world to propose AI policy frameworks to …

Trustworthy machine learning and artificial intelligence Page 1 26 feature XRDS • SPRING
2019 • VOL.25 • NO.3 Math Destruction by Cathy O’Neil, catalogs numerous examples of …

It is common practice in deep learning to use overparameterized networks and train for as
long as possible; there are numerous studies that show, both theoretically and empirically …

Trusting Artificial Intelligence (AI) is controversial since models and predictions might not be
fair, understandable by humans, robust against adversaries, or trained appropriately …

We study the problem of training certifiably robust models against adversarial examples.
Certifiable training minimizes an upper bound on the worst-case loss over the allowed …

Adversarial Robustness Toolbox (ART) is a Python library supporting developers and
researchers in defending Machine Learning models (Deep Neural Networks, Gradient …

Machine learning (ML) has advanced dramatically during the past decade and continues to
achieve impressive human-level performance on nontrivial tasks in image, speech, and text …

Phenomenon-specific" adversarial" datasets have been recently designed to perform
targeted stress-tests for particular inference types. Recent work (Liu et al., 2019a) proposed …

Batch Normalization (BatchNorm) is effective for improving the performance and
accelerating the training of deep neural networks. However, it has also shown to be a cause …