Adversarial Examples: Attacks and Defenses for Deep Learning — mentioned by madmax96

Wed, 20 Mar 2019 20:59:58 GMT

Consider how widely affected contemporary machine learning models are by adversarial examples [1]. I don't know the specific approach used by Tesla or their release process, but I would not be surprised at all if their software has similar shortcomings. Granted, a ton of active research is going on trying to prevent these sorts of problems, but it definitely isn't a solved problem. Basically, ask yourself this: how robust is this software? How are you measuring that? [1] https://arxiv.org/pdf/1712.07107.pdf

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

Adversarial Examples: Attacks and Defenses for Deep Learning · HackerPapers discussions

Adversarial Examples: Attacks and Defenses for Deep Learning — mentioned by madmax96