Threat of adversarial attacks on deep learning in computer vision: A survey
Deep learning is at the heart of the current rise of artificial intelligence. In the field of
computer vision, it has become the workhorse for applications ranging from self-driving cars …
computer vision, it has become the workhorse for applications ranging from self-driving cars …
Adversarial risk bounds via function transformation
We derive bounds for a notion of adversarial risk, designed to characterize the robustness of
linear and neural network classifiers to adversarial perturbations. Specifically, we introduce …
linear and neural network classifiers to adversarial perturbations. Specifically, we introduce …
Intrinsic geometric vulnerability of high-dimensional artificial intelligence
L Bortolussi, G Sanguinetti - arXiv preprint arXiv:1811.03571, 2018 - arxiv.org
The success of modern Artificial Intelligence (AI) technologies depends critically on the
ability to learn non-linear functional dependencies from large, high dimensional data sets …
ability to learn non-linear functional dependencies from large, high dimensional data sets …
Oversight of Unsafe Systems via Dynamic Safety Envelopes
D Manheim - arXiv preprint arXiv:1811.09246, 2018 - arxiv.org
This paper reviews the reasons that Human-in-the-Loop is both critical for preventing widely-
understood failure modes for machine learning, and not a practical solution. Following this …
understood failure modes for machine learning, and not a practical solution. Following this …