Lecturer: Barbara Hammer
Fields: Machine Learning / AI safety
Deep networks are prone to a number of attacks: data poisoning, backdoor attacks, adversarial examples, etc. In particular the latter have gained a lot of attention recently, since they display a shockingly different behavior of humans and machines, which can lead to severe threats in safety critical domains such as autonomous driving or automated border control. In the talk, I will give an overview about recent forms of attacks on deep neural networks, and have a glimpse on attempts of defenses such as adversarial training and further insights on what these findings tell us about the peculiarities of deep networks.
- Chakraborty, Alam, Dey, Chattopadhyay, and Mukhopadhyay (2018). Adversarial Attacks and Defences: A Survey. arXiv:1810.00069
- Machado, Silva, and Goldschmidt (2020). Adversarial Machine Learning in Image Classification: A Survey Towards the Defender’s Perspective. arXiv:2009.03728
Barbara Hammer is a full Professor for Machine Learning at the CITEC Cluster at Bielefeld University, Germany. She received her Ph.D. in Computer Science in 1999 and her venia legendi (permission to teach) in 2003, both from the University of Osnabrueck, Germany, where she was head of an independent research group on the topic ‘Learning with Neural Methods on Structured Data’. In 2004, she accepted an offer for a professorship at Clausthal University of Technology, Germany, before moving to Bielefeld in 2010. Barbara\’s research interests cover theory and algorithms in machine learning and neural networks and their application for technical systems and the life sciences, including explainability, learning with drift, nonlinear dimensionality reduction, recursive models, and learning with non-standard data. Barbara has been chairing the IEEE CIS Technical Committee on Data Mining and Big Data Analytics, the IEEE CIS Technical Committee on Neural Networks, and the IEEE CIS Distinguished Lecturer Committee. She has been elected as member of the IEEE CIS Administrative Committee and the INNS Board. She is an associate editor of the IEEE Computational Intelligence Magazine, the IEEE TNNLS, and IEEE TPAMI. Currently, large parties of her work focusses on explainable machine learning for spatial-temporal data in her role as a PI of the ERC Synergy Grant Water-Futures.
Affiliation: Bielefeld University