Monday, June 14

10:00 - 12:45 Scientific Workshop "Software and Resilience" Part I
Program
Zoom-Link
15:00 - 16:45 Scientific Workshop "Software and Resilience" Part II
Program
Zoom-Link

Tuesday, June 15

13:00 - 13:30 emergenCITY - MAKI DLS Impulse
Lecture “Learning over Graphs” by Prof. Ali Sayed
Abstract This talk explains how agents over a graph can learn from dispersed information and solve inference tasks of varying degrees of complexity through localized processing. The presentation also shows how information or misinformation is diffused over graphs, how beliefs are formed, and how the graph topology helps resist or enable manipulation. Examples will be considered in the context of social learning, teamwork, distributed optimization, and adversarial behavior.
Short Biography Since 2017, A. H. Sayed is Dean of Engineering at EPFL, Switzerland, where he directs the Adaptive Systems Laboratory. He has served as distinguished professor at UCLA (2001-present) where he also held the position of Chairman of Electrical Engineering between 2005 and 2010, having previously been Vice-Chairman from 2002 to 2005. Prior to this he served as Associate Professor of Electrical Engineering at UCLA (1996-2001) and as Assistant Professor of Electrical and Computer Engineering at UCSB (1993-1996) after he started his career at Stanford University as a Research Associate in 1992.Prof. Sayed’s research interests span several areas including adaptation and learning theories, data and network sciences, statistical inference, multi-agent networks, and biologically-inspired designs.
Zoom-Link
DLS Impulse is part of the joint emergenCITY-MAKI Distinguished Lecture Series.
13:30 - 14:00 Kick off emergenCITY Week
Welcome and Introduction
Zoom-Link

14:00 - 15:30

Internal Event

Presentation of program areas to Scientific Advisory Board

15:30 - 17:00

Workshop Digitalethik

Workshop for emergenCITY WiMis, organized by ZEVEDI

Wednesday, June 16

13:30 - 13:55 emergenCITY-MAKI DLS Impulse
Lecture “AI for orbital-terrestrial networks – key technology for global wireless connectivity” by Prof. Armin Dekorsy
Abstract The need for reliable and ubiquitous connectivity is driving the evolution of purely terrestrial networks towards 3-D orbital-terrestrial networks that tightly integrate 5G/6G base stations with High-Altitude -Platforms (HAPS), LEO constellations and GEO satellites in space into an overall network.
Due to their high complexity, such communication systems need to act as autonomously as possible to adapt agilely to e.g. dynamic service requirements of broadband/IoT services, load balancing and interference conditions. Recent results of research and development work on the application of AI/ML in terrestrial networks (5G/6G) motivate the use of these innovations for 3D networks, adapting AI/ML techniques in particular to space requirements.
The presentation will highlight corresponding challenges and technological advantages. For the design of baseband, routing and network slicing, examples will be given on a suitable division into on-ground/in-space learning, the use of deterministic motion profiles of satellites and the generalizability of ML methods. With respect to hardware architectures, the merits of general-purpose computing units and the parallelism of deep neural networks (DNNs), as well as the usability of ML-based COTS components, are highlighted. These examples demonstrate the potential of AI/ML to reduce power consumption, hardware implementation space, and cost while maintaining the overall system autonomy required.
Short Biography Since 2010 Prof. Armin Dekorsy is theProfessor for Communications Engineering and head of the Department of Communications Engineering at University of Bremen where he also started his career as a research assistant in 1996. From 2000 to 2001 he worked as a research and development engineer at T-Nova, Darmstadt, before he got an engagement as a research engineer and project manager at Bell-Labs Europe, Alcatel-Lucent Deutschland GmbH, Nürnberg (2001-2007). In 2007, he joined the Qualcomm CDMA Technologies GmbH in Nürnberg as Research Coordinator Europe before he went back to Bremen in 2010.He investigates new lines of research in wireless communications and signal processing for the baseband of transceivers which can 4The ResilientDigital Cityreadily be transferred to industry. His current research directions include distributed information/signal processing, compressive sensing, machine learning inference/decision methods, and 5G/6G communications such as massive machine type, ultra reliable low latency and LEO satellite communications.
Zoom-Link
DLS Impulse is part of the joint emergenCITY-MAKI Distinguished Lecture Series

14:00 - 15:30

Internal Event

Presentation of program areas to Scientific Advisory Board

16:00 - 17:15 Webinar "Krisenfest durch dunkle Zeiten . Wie resilient sind Kommunen gegenüber Stromausfällen?"
Program
External Event organized by Prof. Michèle Knodt and Schader Stiftung

Thursday, June 17

13:30 - 14:00 emergenCITY-MAKI DLS Impulse
Lecture “Manipulating Machine Learning – Attacks and Countermeasures” by Prof. Cristina Nita-Rotaru
Abstract As more applications with large societal impact rely on machine learning for automated decisions, several concerns have emerged about potential vulnerabilities introduced by machine learning algorithms. Sophisticated attackers have strong incentives to manipulate the results and models generated by machine learning algorithms to achieve their objectives. Attacks against machine learning models can take place at both training and testing time.
In this talk I will first present our work on attacks at testing time, also known as evasion attacks, against classification and regression models for self-driving car applications, specifically steering angle prediction. I will then show attacks at training time, also known as poisoning attacks, where attackers inject a small number of corrupted points in the training data with the goal to change the accuracy of the trained model. I will describe our proposed approach to constructing a defense algorithm called TRIM, which provides high robustness and resilience against a large class of poisoning attacks. I will conclude by pointing out ongoing challenges in ensuring security and privacy in recent applications of machine learning such as federated learning.

This work is based on the following two articles:
  1. Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning. Matthew Jagielski, Alina Oprea, Battista Biggio, Chang Liu, Cristina Nita-Rotaru, and Bo Li. In Proceedings of the IEEE Symposium on Security and Privacy, 2018.
  2. Are Self-Driving Cars Secure? Evasion Attacks against Deep Neural Networks for Steering Angle Prediction. Alesia Chernikova, Alina Oprea, Cristina Nita-Rotaru and Baekgyu Kim. IEEE Workshop on the Internet of Safe Things, Co-located with IEEE Security and Privacy 2019.
Short Biography Cristina Nita-Rotaru is a Professor of Computer Science in the Khoury College of Computer Sciences at Northeastern University (since 2015) where she leads the Network and Distributed Systems Security Laboratory (NDS2). Prior to joining Northeastern she was a faculty in the Department of Computer Science at Purdue University (2003 -2015). She served as Associate Dean of Faculty atNortheastern University (2017 -2020) and as an Assistant Director for CERIAS at Purdue University (2011 -2013).
Her research lies at the intersection of security, distributed systems, and computer networks. The overarching goal of her work is designingand building secure and resilient distributed systems and network protocols, with assurance that deployed implementations provide their security, resilience, and performance goals. Her work received several best paper awards in IEEE SafeThings 2019, NDSS 2018, ISSRE 2017, DSN 2015 as well as two IETF/IRTF Applied Networking Research Prize in 2018 and 2016. She is a recipient of the NSF Career Award in 2006.
Zoom-Link
DLS Impulse is part of the joint emergenCITY-MAKI Distinguished Lecture Series

14:00 - 16:30

Internal Event

Presentation of missions to Scientific Advisory Board