4th ACM Computer Science in Cars Symposium - Online (CSCS 2020)

Conference Proceedings Conference Program Keynote Speakers Conference Comittee

The CSCS is ACM’s flagship Car IT event. We are bringing together the likes of scientists, engineers, business representatives and everyone who shares a passion for solving the myriad of complex problems of in-vehicular technology and it’s application in automation, driver/vehicular safety, and driving system security.

This year we are happy to invite you to the symposium to discuss future challenges in artificial intelligence and security for autonomous vehicles.
Due to the coronavirus pandemic situation, we are welcoming you online for an exciting online conference experience. Expect exciting interactive opportunities with the presenters throughout the whole day.


09:0010:00Keynote: Artificial Intelligence in Automotive Engineering
Dr.-Ing. Steven Peters (Mercedes Benz AG)
10:0011:00Full Paper Session: AI, Evaluation and Testing
  • MonoComb: A Sparse-to-Dense Combination Approach for Monocular Scene FlowRené Schuster (DFKI), Christian Unger (BMW), Didier Stricker (DFKI)
  • Frenet Coordinate Based Driving Maneuver Prediction at Roundabouts Using LSTM NetworksCarina Vogl (Audi), Moritz Sackmann (Friedrich-Alexander-Universität Erlangen), Ludwig Kürzinger (Technische Universität München), Ulrich Hofmann (Audi)
  • A Self-Supervised Feature Map Augmentation (FMA) Loss and Combined Augmentations Finetuning to Efficiently Improve the Robustness of CNNsNikhil Kapoor (Volkswagen AG), Chun Yuan (Volkswagen AG), Jonas Löhdefink (Technische Universität Braunschweig), Roland Zimmerman (Universität Goettingen), Serin Varghese (Volkswagen AG), Fabian Hüger (Volkswagen Group Automation), Nico M. Schmidt (Volkswagen AG), Peter Schlicht (Volkswagen Group Research), Tim Fingscheidt (Technische Universität Braunschweig)
  • DNN Analysis through Synthetic Data VariationQutub Syed (INTEL LABS), Oliver Grau (Intel), Korbinian Hagn (Intel)
  • Distributed Model-Free Ride-Sharing Algorithm with Pricing using Deep Reinforcement LearningMarina W. Haliem (Purdue University), Ganapathy Mani (Purdue University), Vaneet Aggarwal (Purdue University), Bharat Bhargava (Purdue University)
11:0012:15Extended Abstract Session: Spotlights
  • Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic GuidanceMarvin Klingner (Technische Universität Braunschweig ), Jan-Aike Termöhlen (Technische Universität Braunschweig), Jonas Mikolajczyk (Technische Universität Braunschweig), Tim Fingscheidt ( Technische Universität Braunschweig)
  • Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image SegmentationYang He (CISPA Helmholtz Center for Information Security), Shadi Rahimian (CISPA Helmholtz Center for Information Security), Bernt Schiele (MPI Informatics), Mario Fritz (CISPA Helmholtz Center for Information Security)
  • Robust Semantic Segmentation by Redundant Networks With a Layer-Specific Loss Contribution and Majority VoteAndreas Bär (Technische Universität Braunschweig), Marvin Klingner (Technische Universität Braunschweig ), Serin Varghese (Volkswagen AG), Fabian Hüger (Volkswagen Group Automation), Peter Schlicht (Volkswagen Group Research), Tim Fingscheidt ( Technische Universität Braunschweig)
  • Haar Wavelet based Block Autoregressive Flows for TrajectoriesApratim Bhattacharyya (Max Planck Institute for Informatics), Christoph-Nikolas Straehle (Bosch Center for Artificial Intelligence), Mario Fritz (CISPA Helmholtz Center for Information Security), Bernt Schiele (MPI Informatics)
  • Safety Concerns and Mitigation Approaches Regarding the Use of Deep Learning in Safety-Critical Perception TasksShervin Raafatnia (Bosch), Stephanie Abrecht (Robert Bosch GmbH), Sebastian Sudholt (Robert Bosch GmbH)
  • Adversarial Attacks on Speech Recognition Systems: Language Bias in LiteratureKarla Markert (Fraunhofer AISEC), Donika Mirdita (Fraunhofer AISEC), Konstantin Böttinger (Fraunhofer AISEC)
  • FlexPool: A Distributed Model-Free Deep Reinforcement Learning Algorithm for Joint Passengers \& Goods TransportationKaushik Bharadwaj Manchella (Purdue University), Abhishek Kumar Umrawal (Purdue University), Vaneet Aggarwal (Purdue University)
  • Joint Detection and Tracking for Efficient Scene UnderstandingIssa Mouawad (University of Genoa), Francesca Odone ("University of Genova, Italy")
  • DNN Optimization in Low-Power Speech ProcessingMunir Georges (THI)
  • Towards Automated Testing and Robustification by Semantic Adversarial Data GenerationRakshith Shetty (Max Planck Institute of Informatics), Mario Fritz (CISPA Helmholtz Center for Information Security), Bernt Schiele (MPI Informatics)
  • Characterizing Data Sets for training and validation in automated drivingPeter Nöst (Intel), Korbinian Hagn (Intel), Oliver Grau (Intel)
  • Increasing realism of synthetic datasets through additive sensor and lens artefactsKorbinian Hagn (Intel), Oliver Grau (Intel)
  • Cyber-Secure City Transport EcosystemAndrew J. Roberts (Tallinn University of Technology)
12:1513:15- Breakout Session for Discussion -
13:1514:15Keynote: Recent Methods from Computer Vision for Perception in Highly Automated Driving
Prof. Dr.-Ing. Tim Fingscheidt (TU Braunschweig)
14:1515:30Full Paper Session: Security
  • Privacy by Design: Survey on Capacitive Proximity Sensing as System of Choice for Driver Vehicle InterfacesSebastian Frank (TU Darmstadt), Arjan Kuijper (Fraunhofer Institute for Computer Graphics Research IGD and Mathematical and Applied Visual Computing Group, TU Darmstadt)
  • Transport Layer Scanning for Attack Surface Detection in Vehicular NetworksNils H. Weiss (University of Applied Sciences Regensburg)
  • A Hybrid Model for Safety and Security Assessment of Autonomous VehiclesRhea Rinaldo (German Research Center for Artificial Intelligence (DFKI)), Timo F. Horeis (Institut für Qualitäts- und Zuverlässigkeitsmanagement GmbH)
  • Grey-box Analysis and Fuzzing of Automotive Electronic Components via Control-Flow Graph ExtractionAndreea-Ina Radu (University of Birmingham), Flavio Garcia (University of Birmingham)
  • Autonomous Vehicles: Data Protection and Ethical ConsiderationsIoannis Krontiris (Huawei Technologies), Kalliroi Grammenou (Luxembourg Data Protection Authority), Kalliopi Terzidou (Leiden University), Marina Zacharopoulou (University of Bologna), Marina Tsikintikou (University of Luxembourg), Foteini Baladima (Rheinische-Friedrich-Wihlelms University of Bonn), Chrysi Sakellari (Toyota Motor Europe), Konstantinos Kaouras (University College London)
  • Security Analysis of Automotive ProtocolsTimm Lauser (Hochschule Darmstadt), Daniel Zelle (Fraunhofer SIT), Christoph Krauß (Fraunhofer SIT)
  • HIP-20: Integration of Vehicle-HSM-Generated Credentials into Plug-and-Charge InfrastructureAndreas Fuchs (Fraunhofer SIT), Dustin Kern (Fraunhofer SIT), Christoph Krauß (Fraunhofer SIT), Maria Zhdanova (Fraunhofer SIT), Ronald Heddergott (Carmeq GmbH)
15:3016:00- Breakout Session for Discussion -
16:0017:00Keynote: Cyber Security Challenges & Solutions in the Automotive Industry
Dr.-Ing. Mathias Dehm (Continental)

All dates are UTC+1 / CET

Keynote Speakers

Dr.-Ing. Mathias Dehm


Dr.-Ing. Steven Peters

Mercedes-Benz AG

Prof. Dr.-Ing. Tim Fingscheidt

TU Braunschweig

Conference Committee

Björn Brücher


Björn Brücher is a technical lead in computer cloud graphics at Intel in Germany and the General Chair of the CSCS conference this year. He is an experienced professional in computer science with broad technical acumen across CPU & GPU in hardware and software with extensive experience in software development, optimization, and validation. As a trusted advisor and industry influencer he led projects in the autonomous driving area in close collaboration with German car manufactures. Most of his professional life he focused on computer graphics and high-performance computing. He holds a master’s degree in electrical engineering from the University of Siegen, Germany. Preservation of the environment, green energy, and electromobility are what he is interested in. Implementing innovative solutions in private life, proven to work, and being vocal about it in public.

Oliver Wasenmüller

Mannheim University for Applied Science

Oliver Wasenmüller is full Professor at the Mannheim University for Applied Science. His research is in the intersection of Computer Vision and Artificial Intelligence with a focus on automotive. Previously he was a team leader for "machine vision and autonomous vehicles" at the German Research Center for Artificial Intelligence (DFKI). He is both speaker and reviewer in many scientific conferences in this field and co-organizes also the IEEE CVPR workshop SAIAD.

Mario Fritz

CISPA Helmholtz Center for Information Security

Mario Fritz is faculty member at the CISPA Helmholtz Center for Information Security, Saarbruecken, Germany and professor at the Saarland University. Previously, he was senior researcher at the Max Planck Institute for Informatics and post-doc at UC Berkeley and the International Computer Science Institute on a Feodor Lynen Research Fellowship of the Alexander von Humboldt Foundation. His research focus is at the intersection of Artificial Intelligence & Machine Learning with Security & Privacy. His recent work focuses on Deep Learning techniques that allow end-to-end training of complex and multi-modal approaches. He has over 90 publications - 50 in top venues. His key contributions include work on visual domain adaptation, latent factor models, the Visual Turing Test, privacy in visual data, and attack as well as defenses for machine learning models. He has served as area chair for ECCV and ICCV, is associate editor of TPAMI and is member of the ACM Europe Technology Policy Committee.

Hans-Joachim Hof

Technische Hochschule Ingolstadt

Hans-Joachim Hof is full professor and vice president of Technische Hochschule Ingolstadt, Germany. He leads the research group „Security in Mobility“ in the CARISSMA Institute of Electric, Connected, and Secure Mobility (C-ECOS). His research focus is on the security testing of vehicles as well as on secure automotive software. Previously, Hans-Joachim was a full professor at the Munich University of Applied Sciences, Germany and research scientist at Corporate Technology of Siemens AG, Germany. He holds a PhD from the Karlsruhe Institute of Technology, Germany. Hans-Joachim is a member of  the board of the German Chapter of the ACM and of the German national computer science association (Gesellschaft für Informatik).

Christoph Krauß

Darmstadt University of Applied Sciences and INCYDE GmbH

Prof. Dr. Christoph Krauß is full professor for Network Security, spokesperson of the IT Security expert group, and head of the research group Applied Cyber Security Darmstadt (ACSD) at Darmstadt University of Applied Sciences. Furthermore, he is Head of Automotive Security Research at INCYDE GmbH, which he co-founded. At the National Research Center for Applied Cybersecurity ATHENE, he is Principal Investigator and coordinator of the research area Secure Autonomous Driving. He has over 15 years of experience in IT security. His research and interests include automotive security and privacy, railway security, intelligent energy networks security, trusted computing, network security, efficient and post-quantum cryptography, and security engineering.

Oliver Grau


Oliver Grau works for Intel Labs in Germany on topics of automated driving. He joined Intel as co-director of the Intel-Visual Computing Institute and he worked previously as a Lead Technologist for BBC R&D in London, UK on computer vision projects for innovative media production systems.

Isha Sharma


Isha is a Graphics Software Engineer at Intel. She is currently involved in the development of Intel's oneAPI rendering toolkit and received her master's degree from RWTH Aachen. Her core interests include ray-tracing and physically-based rendering.

Kevin Gomez


Kevin is a research associate at the CARISSMA Institute of Electric, Connected, and Secure Mobility (C-ECOS). His research focuses on new methods and techniques in the field of digital forensics of vehicles. He is currently pursuing his PhD at the Friedrich-Alexander-University Erlangen-Nürnberg in cooperation with the Technical University Ingolstadt. Prior to his academic career, Kevin worked as a Security Incident Responder at Audi AG for more than 4 years.

Thank you to our valued Sponsors