Adversarial Machine Learning: How Secure Is Machine Learning?
As Machine Learning is increasingly integrated in many applications, including safety critical ones such as autonomous cars, robotics, visual authentication and voice control, wrong predictions can have a significant influence on individuals and groups.
Advances in prediction accuracy have been impressive, and while machine learning systems still can make rather unexpected mistakes on relatively easy examples, the robustness of algorithms has also steadily increased. However, many models, and specifically Deep Learning approaches and image analysis, are rather susceptible to adversarial attacks.
This talk will give an overview on various attacks (backdoors, evasion, inference/inversion), and will show they could be mitigated.
sec4dev Conference & Bootcamp
The sec4dev Conference & Bootcamp is a Vienna-based security event which targets one very specific group: people involved in software development. It is our mission to bring together the best industry professionals, thus having a sustainable and positive impact on the software security landscape.