More talks in the program:
As machine learning (ML) based approaches continue to achieve great results and their use becomes more widespread, it becomes increasingly more important to examine their behavior in adversarial settings. Unfortunately, ML models have been shown to be vulnerable to so-called adversarial examples, inputs to ML models that are intentionally designed to cause them to malfunction. Despite the ongoing research efforts there is no reliable solution so far, meaning that today’s state of the art learning-based approaches remain vulnerable.
In this talk, we will take a look at things an ML practitioner should know when it comes to security issues in ML systems, with a focus on vulnerabilities at test time.