Introduction
A clear advantage of virtual conferences is that all talks and keynotes get recorded and are available on demand. For me, ICML'20 was the first conferences for which I had to record my talk. The paper I presented at ICML'20 deals with robustness to adversarial examples. In particular, compared to standard adversarial training, it improves robustness to adversarial examples not seen during training — for example, $L_2$ adversarial examples when training on $L_\infty$ ones. This is achieved by biasing the network towards uniform predictions on adversarial examples during training. As shown in the paper, this behavior extends beyond the $L_\infty$ ball used for adversarial examples during training. As result, adversarial examples can easily be rejected by confidence thresholding. Find the talk, paper and slides below.
Slides Paper on ArXivTalk
There are also some interesting talks from many of my colleagues:
- More talks from Matthias Hein's group on adversarial robustness: Matthias Hein on SlidesLive
- Talks from Bernt Schiele's group: Bernt Schiele on SlidesLive