The following two MPI-SWS papers have been accepted to ICML 2020, one of the flagship conferences in machine learning: Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning by Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu, Adish Singla. Adaptive Reward-Poisoning Attacks against Reinforcement Learning by Xuezhou Zhang, Yuzhe Ma, Adish…
Research by MPI-SWS faculty member Elissa Redmiles and collaborators at Microsoft Research, the University of Zurich, the University of Maryland and Johns Hopkins University was featured in the New York Times, Scientific American (article 1, article 2), Wired (article 1, article 2), STAT News, and other venues. The articles cover two papers: (1) Redmiles' paper…
MPI-SWS researchers Sergey Bozhko and Björn Brandenburg have received an Outstanding Paper Award at the 32nd Euromicro Conference on Real-Time Computing Systems (ECRTS 2020) for their paper entitled Abstract Response-Time Analysis: A Formal Foundation for the Busy-Window Principle. Congratulations!
MPI-SWS researchers Arpan Gujarati, Sergey Bozhko, and Björn Brandenburg have received a Distinguished Paper Award at the 26th IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS 2020) for their paper entitled “Real-Time Replica Consistency over Ethernet with Reliability Bounds”. Congratulations!
Due to the impressive advances in Machine Learning and the unlimited availability of data, neural networks are rapidly becoming prevalent in our everyday lives, for instance by assisting in image-classification or decision-making tasks. As a result, there is growing concern regarding the reliability of neural networks in performing these tasks.…
