NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles · HackerPapers discussions

NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles — mentioned by dontreact

Fri, 03 Nov 2017 00:14:09 GMT

Was there a follow up to this paper? NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles https://arxiv.org/abs/1707.03501

Paper and discussion history. A mention is not an endorsement.

NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles — mentioned by moyix

Sat, 05 Aug 2017 15:06:00 GMT

There was a paper that claimed those sorts of rotations and movements can help alleviate adversarial examples: https://arxiv.org/abs/1707.03501 However, OpenAI quickly refuted it by creating adversarial examples that continue to fool the classifier even when rotated, scaled, etc: https://blog.openai.com/robust-adversarial-inputs/ So it looks like there's no "easy" way out here. Multiple types of sensors may help, but it seems likely that it will still be possible to construct examples that fool network over all sensor inputs at once. Ian Goodfellow and Nicolas Papernot have a good blog on…

Paper and discussion history. A mention is not an endorsement.

NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles — mentioned by swordswinger12

Sat, 29 Jul 2017 22:08:12 GMT

This paper is a fairly convincing counter-argument to another recent work (https://arxiv.org/abs/1707.03501) on physical adversarial examples for autonomous vehicles. The other paper argued there was "no need to worry" about such physical attacks.

Paper and discussion history. A mention is not an endorsement.

NO Need to Worry about Adversarial Examples in Object Detection in Autonomous Vehicles — HN submission

Sat, 15 Jul 2017 02:04:22 GMT

NO Need to Worry about Adversarial Examples for Autonomous Vehicles

5 points; 1 discussion reply on HN. Paper and source history. A submission is not an endorsement.