Machine learning has evolved into an enabling technology for a wide range of highly
successful applications. The potential for this success to continue and accelerate has placed …

Data poisoning attacks and backdoor attacks aim to corrupt a machine learning classifier via
modifying, adding, and/or removing some carefully selected training examples, such that the …

Adversarial Robustness for Machine Learning summarizes the recent progress on this topic
and introduces popular algorithms on adversarial attack, defense and veri? cation. Sections …

Randomized smoothing is a popular method to certify robustness of image classifiers to
adversarial input perturbations. It is the only certification technique which scales directly to …

Nearest prototype classifiers (NPCs) assign to each input point the label of the nearest
prototype with respect to a chosen distance metric. A direct advantage of NPCs is that the …

Methods for adversarial robustness certification aim to provide an upper bound on the test
error of a classifier under adversarial manipulation of its input. Current certification methods …

Conditional estimation given specific covariate values (ie, local conditional estimation or
functional estimation) is ubiquitously useful with applications in engineering, social and …

The introduction of 5G technology along with the exponential growth in connected devices is
expected to cause a challenge for the efficient and reliable network resource allocation …

We study the certification of stability properties, such as robustness and individual fairness,
of the k-Nearest Neighbor algorithm (kNN). Our approach leverages abstract interpretation …

Adversarial black-box attacks aim to craft adversarial perturbations by querying input–output
pairs of machine learning models. They are widely used to evaluate the robustness of pre …