Training Deep Neural Networks (DNNs) that are robust to norm bounded adversarial attacks remains an elusive problem. While verification based methods are generally too expensive to robustly train large networks, it was demonstrated in Gowal et al …
Despite the impressive performance of Deep Neural Networks (DNNs) on various vision tasks, they still exhibit erroneous high sensitivity toward semantic primitives (e.g. object pose). We propose a theoretically grounded analysis for DNNs robustness …
One major factor impeding more widespread adoption of deep neural networks (DNNs) is their lack of robustness, which is essential for safety-critical applications such as autonomous driving. This has motivated much recent work on adversarial attacks …