Publications

• The need for systematic approaches in risk assessment of safety-critical AI-applications in machinery
  Franziska Wolny, Silvia Vock, Rasmus Adler, Taras Holayad
  Prceedings of the European Safey and Reliability Conference (ESREL), Stavanger/Norway, June 15, 2025
  
  The integration of artificial intelligence (AI) into safety-critical machinery applications in industrial environments presents substantial challenges for conformity assessment and safety certification.
  Read more
• Dynamic Risk Assessment for Human-Robot Collaboration Using a Heuristics-based Approach
  Georgios Katranis, Frederik Plahl, Joachim Grimstadt, Ilshat Mamaev, Silvia Vock, Andrey Morozov
  , January 21, 2025
  
  Human-robot collaboration (HRC) introduces significant safety challenges, particularly in protecting human operators working alongside collaborative robots (cobots). While current ISO standards emphasize risk assessment and hazard identification, these procedures are often insufficient for addressing the complexity of HRC environments, which involve numerous design factors and dynamic interactions.
  Read more
• From Classical to Advanced Risk Methods: Demonstrator for Industrial Cyber-Physical Systems
  Andrey Morozov, Tagir Fabarisov, Silvia Vock, Thorben Schey, Artur Karimov, Georg Siedel, Joachim Grimstad, Arne Sonnenburg, Thomas Mossner
  , January 14, 2025
  
  Modern industrial Cyber-Physical Systems (CPS) exhibit high levels of reconfigurability and heterogeneity, posing significant challenges for risk assessment in dynamic environments. Traditional risk assessment methods, originally developed for simpler systems
  Read more
• A Time-series Data Generation Tool for Risk Assessment of Robotic Applications
  Yuliang Ma, Apurv Patel, Don Kurian, Julien Siebert, Silvia Vock, Andrey Morozov
  , January 12, 2025
  
  Robotic systems increasingly rely on artificial intelligence (AI) to enhance their capabilities in performing complex tasks across various domains. The development and evaluation of AI systems usually require high-quality datasets
  Read more
• A practical approach to evaluating the adversarial distance for machine learning classifiers
  Siedel, G., Gupta, E., Morozov, A.
  Proceedings of the ASME 2024 International Mechanical Engineering Congress and Exposition (IMECE), November 17, 2024
  
  Adversarial distance is a highly informative measure of robustness that enjoys little attention in the adversarial robustness domain. We built a practical attack algorithm to evaluate this measure more effectively than implementations in the popular Adversarial Robustness Toolbox (ART). We also combine this upper-bound estimator with the popular lower-bound estimation method CLEVER, showing CLEVERs inability to calculate a correct lower bound in many cases.
  Read more
• Improved Dimensionality Dependence for Zeroth-Order Optimisation over Cross-Polytopes
  Weijia Shao
  , July 29, 2024
  
  This work proposes an algorithm improving the dimensionality dependence for gradient-free optimisation over cross-polytopes, which has many applications such as adversarial attacks, explainable AI and sparse regression.
  Read more
• Investigating the Corruption Robustness of Image Classifiers with Random p-norm Corruptions
  Siedel, G., Shao, W., Vock, S., Morozov, A.
  Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP, February 29, 2024
  
  We show that image classifiers are not only vulnerable to invisible adversarial noise, but also to invisible random noise, and propose a corresponding metric. We also find that training data augmentation with a combination of p-norm noise types contributes more to corruption robustness than common noise injection.
  Read more
• Adaptive Zeroth-Order Optimisation of Nonconvex Composite Objectives
  Weijia Shao, Sahin Albayrak
  , September 19, 2022
  
  In this paper, we propose and analyse algorithms for zeroth-order optimisation of non-convex composite objectives, focusing on reducing the complexity dependence on dimensionality. This is achieved by exploiting the low dimensional structure of the decision set using the stochastic mirror descent method with an entropy alike function, which performs gradient descent in the space equipped with the maximum norm
  Read more
• Optimistic optimisation of composite objective with exponentiated update
  Weijia Shao, Fikret Sivrikaya and Sahin Albayrak
  , August 22, 2022
  
  This paper proposes a new family of algorithms for the online optimisation of composite objectives. The algorithms can be interpreted as the combination of the exponentiated gradient and p-norm algorithm.
  Read more
• Utilizing Class Separation Distance for the Evaluation of Corruption Robustness of Machine Learning Classifiers
  Georg Siedel, Silvia Vock, Andrey Morozov, Stefan Voß
  , June 27, 2022
  
  Robustness is a fundamental pillar of Machine Learning (ML) classifiers, substantially determining their reliability. Methods for assessing classifier robustness are therefore essential. In this work, we address the challenge of evaluating corruption robustness in a way that allows comparability and interpretability on a given dataset. We propose a test data augmentation method that uses a robustness distance derived from the datasets minimal class separation distance.
  Read more
• KrakenBox: Deep Learning-Based Error Detector for Industrial Cyber-Physical Systems
  Sheng Ding, Andrey Morozov, Tagir Fabarisov, Silvia Vock
  , January 25, 2022
  
  Online error detection helps to reduce the risk of failure of safety-critical systems. However, due to the increasing complexity of modern Cyber-Physical Systems and the sophisticated interaction of their heterogeneous components, it becomes harder to apply traditional error detection methods
  Read more
• An Overview of the Research Landscape in the Field of Safe Machine Learning
  Georg Siedel, Stefan Voß, Silvia Vock
  , January 25, 2022
  
  The applicability of ML components in safety-critical systems will significantly depend on whether it will be possible to provide a comprehensive proof of their safety. Three research questions (RQ) are answered in order to provide a starting point for future activities towards the risk assessment of safety-critical systems containing ML components.
  Read more
• An Integrative and Transdisciplinary Approach for a Human-Centered Design of AI-Based Work Systems
  Larissa Schlicht, Marlen Melzer, Ulrike Rösler, Stefan Voß, Silvia Vock
  , January 25, 2022
  
  Psychological and ethical criteria are to date not systematically covered in the system design process. We suggest to extend existing model-based system engineering approaches by new elements that are capable to capture these criteria and, in particular, allow for an implementation of psychological risk analysis and ethical evaluation of work systems already in the design phase.
  Read more
• Sicherheit und Gesundheit in der digitalisierten Arbeitswelt: Kriterien für eine menschengerechte Gestaltung. 2022
  Corinna Weber, Patricia Tegtmeier, Sabine Sommer, Anita Tisch, Sascha Wischniewski
  , January 01, 2022
  
  Roboter, Künstliche Intelligenz, Big Data, mobile Arbeit, Industrie 4.0 - die Arbeitswelt befindet sich im digitalen Wandel. Spürbar ist der Wandel zunächst in den von Menschen ausgeübten Tätigkeiten.Das Buch liefert Antworten auf die Frage, wie stark die Digitalisierung bereits Einzug in unterschiedliche berufliche Tätigkeiten genommen und dadurch die spezifischen Arbeitsanforderungen verändert hat
  Read more
• An Overview of the Research Landscape in the Field of Safe Machine Learning
  Siedel, G., Voß, S., Vock, S.
  Proceedings of the ASME 2021 International Mechanical Engineering Congress and Exposition. Volume 13: Safety Engineering, Risk, and Reliability Analysis; Research Posters, November 05, 2021
  
  In order to provide a systematic overview of research on safe machine learning, we defined a hierarchy of safety-related machine learning properties and visualised the search results in this area in literature maps. We categorised the methods identified in the field according to the machine learning life cycle. Finally, we compared the methods with those required to achieve functional safety of traditional software according to ISO 61508.
  Read more
• Adaptive Online Learning for the Autoregressive Integrated Moving Average Models
  Weijia Shao,Lukas Friedemann Radke,Fikret Sivrikaya and Sahin Albayrak
  , June 29, 2021
  
  This paper addresses the problem of predicting time series data using the autoregressive integrated moving average (ARIMA) model in an online manner. Existing algorithms require model selection, which is time consuming and unsuitable for the setting of online learning.
  Read more
• Sichere Maschinen mit - oder trotz - künstlicher Intelligenz
  C. Mattiuzzo, S. Vock, T. Mössner, S. Voß
  , June 01, 2021
  
  Die Europäische Kommission hat im April nicht nur einen Vorschlag für eine Verordnung zur künstlichen Intelligenz vorgelegt, sondern auch einen Vorschlag für eine Verordnung über Maschinenprodukte mit rechtlich verbindlichen Rahmenbedingungen für die Verwendung künstlicher Intelligenz, welche die Maschinen-Richtlinie 2006/42/EG ablösen soll
  Read more
• When algorithm selection meets Bi-linear Learning to Rank: accuracy and inference time trade off with candidates expansion
  Jing Yuan, Christian Geissler, Weijia Shao, Andreas Lommatzsch, Brijnesh Jain
  , October 09, 2020
  
  Algorithm selection (AS) tasks are dedicated to find the optimal algorithm for an unseen problem instance. With the knowledge of problem instances’ meta-features and algorithms’ landmark performances, Machine Learning (ML) approaches are applied to solve AS problems
  Read more
• Model-Based Error Detection for Industrial Automation Systems Using LSTM Networks
  Sheng Ding, Andrey Morozov, Silvia Vock, Michael Weyrich, Klaus Janschek
  , September 14, 2020
  
  The increasing complexity of modern automation systems leads to inevitable faults. At the same time, structural variability and untrivial interaction of the sophisticated components makes it harder and harder to apply traditional fault detection methods.
  Read more
• Dossier de sécurité pour les machines et équipements connectés dans les usines flexibles
  Silvia Vock, Bjoern Kasper, Stefan Voss
  , March 01, 2020
  
  Article HST (Focus normalisation) extrait du Bulletin 4/19 de la KAN-Brief. Dans les usines flexibles de l'industrie du futur (4.0) aussi, il faut garantir la sécurité des salariés. Du fait du degré élevé de connectivité, il faut se pencher non seulement sur la sécurité fonctionnelle, mais aussi, dans une plus large mesure, sur la sécurité contre les attaques venues de l'extérieur, et sur les interactions entre ces deux aspects.
  Read more
• Sicherheitsnachweis bei digital vernetzten Maschinen und Anlagen in wandelbaren Fabriken
  Silvia Vock, Bjoern Kasper, Stefan Voss
  , December 01, 2019
  
  Auch in wandelbaren Maschinen und Fertigungsanlagen der Industrie 4.0 ist die Sicherheit der Beschäftigten zu gewährleisten. Durch den hohen Vernetzungsgrad muss neben der funktionalen Sicherheit in verstärktem Maße auch die Sicherheit gegen Angriffe von außen und die Wechselwirkungen zwischen beiden Aspekten betrachtet werden.
  Read more
• Industry 4.0: Emerging challenges for dependability analysis
  Andrey Morozov, Silvia Vock, Kai Ding, Stefan Voss, Klaus Janschek
  Industry 4.0, January 01, 2019
  
  Industry 4.0 brings new challenges for the quantitative methods for the evaluation of system dependability properties such as reliability and safety. In this paper, we recall relevant Industry 4.0 and dependability concepts and provide an overview of available reliability and safety metrics and evaluation methods including event trees, fault trees, reliability block diagrams, and more sophisticated dynamic methods based on Markov chain models. The special focus is on the model-based application of these methods.
  Read more