CISPA's Young Researcher Security Convention will take place from April 1 - 5, 2019.
It will give you a deep dive into three hot topics in the areas of System Security, Security Guarantees, and Machine Learning. You will be able to meet and learn from top experts in these fields.
Hot topics in machine learning: Attacks and Defenses for Machine Learning Models
Machine Learning Overview
Machine Learning is a quickly advancing research area that has led to several breakthroughs in the past years. We will give a short introduction into some of the most relevant concepts -- including Deep Learning techniques.
While there has been a leap in performance of machine learning systems in the past decade, still many open issues remain in order to deploy such models in critical systems with guarantees on robustness. In particular, Deep Learning techniques have shown strong performance on a wide range of tasks, but are equally highly susceptible to adversarial manipulation of the input data. Successful attacks that change the output and behavior of an intelligent system can have severe consequences ranging from accidents of autonomous driving systems to by-passing malware or intrusion detection. We cover techniques in the domain of adversarial machine learning that aim at manipulation the predictions of machine learning models and show defenses in order to protect against such attacks.
Machine Learning services are offered by a range of providers that make it easy for clients e.g to enable intelligent services for their business. Based on a dataset, a machine learning model is trained that then can be access e.g. via an online API. The data and the machine learning model itself are important assets and often constitute intellectual property. Our recent research has revealed that such assets leak to customers that use the service. Hence, an adversary can exploit the leaked information to gain access to data and/or the machine learning model by only using the service. We will cover novel inference attacks on machine learning models and show defenses that allow secure and protected deployment of machine learning models.
The success of today’s machine learning algorithms is largely fueled by large datasets. Many domains of practical interest are human centric and are target at operating under real-world conditions. Therefore, gathering real-world data is often key the success of such methods. This is frequently achieved by leveraging user data or crowdsourcing efforts. We will present privacy preserving machine learning techniques that prevent leakage of private information or linking attacks.
66123 Saarbrücken, Germany
Thank you for your application. Participants for SeCon 2019 have been selected.
If you are interested in joining one of our schools/conventions, please check our website for a future schools and security conventions, or follow us on twitter: https://twitter.com/cispa/.