20th European Dependable Computing Conference
8-11 April 2025
Lisbon, Portugal

Keynotes

Towards dependable and secure decentralized machine learning

Sonia Ben Mokhtar
CNRS, INSA Lyon

Date: Wednesday, April 9th, 2025

Abstract: There is a strong momentum towards data-driven services at all layers of society and industry. This started from large scale web-based applications such as Web search engines (e.g., Google, Bing), social networks (e.g., Facebook, TikTok, Twitter, Instagram) and recommender systems (e.g., Amazon, Netflix) and is becoming increasingly pervasive thanks to the adoption of handheld devices and the advent of the Internet of Things. Recent initiatives such as Web 3.0 are coming with the promise of decentralising such services for empowering users with the ability to gain back control over their personal data, and prevent a few economic actors from over concentrating decision power. However, decentralising online services calls for decentralising the data and the machine learning algorithms on which they heavily rely. While Federated Learning allows training machine learning models over decentralised data, it still relies on the centralised computation of model aggregations. In this presentation, I will present recent research works targeting the decentralisation of machine learning beyond the well know Federated Learning concept. A particular focus will be given on recent advances and open challenges for enforcing dependability and security in decentralized machine learning.

Sonia Ben Mokhtar
Sonia Ben Mokhtar is a CNRS research director at the LIRIS laboratory, Lyon, France and the head of the distributed systems and information retrieval group (DRIM). She received her PhD in 2007 from Université Pierre et Marie Curie before spending two years at University College London (UK). Her research focuses on the design of resilient and privacy-preserving distributed systems. Sonia has co-authored 80+ papers in peer-reviewed conferences and journals and has served on the editorial board of IEEE Transactions on Dependable and Secure Computing and co-chaired major conferences in the field of distributed systems (e.g., ACM Middleware, IEEE DSN). Sonia has served as chair of ACM SIGOPS France and as co-chair of GDR RSD a national academic network of researchers in distributed systems and networks.

Navigating the Path to Residual Risk Compliance in AI-Driven Safety Functions

Carles Hernández Luz and Nicholas Mc Guire

Carles Hernández Luz: UPV
Nicholas Mc Guire: OpenTech

Date: Friday, April 10th, 2025

Abstract: Safety-critical systems (SCS) like those included in airplanes, cars, medical devices and nuclear plants go through a stringent domain-specific certification process to validate functional safety properties. The goal of such thorough verification and validation is to reduce the risk of operational failures leading to catastrophic consequences. Recently, there has been a surge of new SCS fueled by artificial intelligence (AI) including fully autonomous driving systems, AI-enabled medical devices, and robotics operators. Safety-related functionalities governed by AI tremendously escalate the complexity of achieving functional safety. The SCS industry is struggling with the necessary shift from low complexity hardware governed applications to these increasingly complex software-controlled systems executed on top of very complex processors. This comes at a time when society is starting to blindly (and dangerously) rely on such complex computing systems. There is thus an urgent need to find new approaches to manage the exponentially growing complexity of SCS in the era of AI. This talk reviews the main challenges associated with meeting functional safety requirements for safety-relevant AI functionalities and introduces a potential approach towards that end.

Carles Luz
Carles Hernández is Ramon y Cajal researcher at Universitat Politecnica de Valencia (UPV) with expertise in reliable and time predictable processor design. Previously (2012-2016) he was senior researcher at BSC. He has been the technical coordinator and principal investigator of H2020 SELENE project targeting the design of an open-source high-performance processor design for safety critical systems. At UPV he is currently the principal investigator of the NimbleAI, and ISOLDE projects. In 2015 he was granted with a Young Researcher Grant (205.000€) by the Spanish MINECO to conduct research on high-performance and reliable processor design. Dr. Hernandez has been research consultant for BSC in the context of the H2020 European Processor Initiative Project Automotive Stream and has published over 100 papers in high-quality conferences and journals.
Nicholas Mc Guire
Nicholas Mc Guire. After working on Magnetic bearing control systems at the Technical University of Vienna (TUV), in 1995 Nicholas moved towards the other end of the spectrum towards clusters at the Inst. for Computational Material Science at the University of Vienna. With the focus shifting to real-time and distributed embedded systems, initially maintaining RTLinux/GPL (2001-2005), safety related systems were an almost natural next step in 2003. Nicholas main topic is system safety since he founded OpenTech, with a special focus on the utilization of FLOSS/COTS components in safety-related systems and thus integration of high-complexity pre-existing (SOUP) components while retaining system level safety properties.

Dependability and Safety in the Railway and Space domains: Challenges, Commonalities and Differences

Nuno Silva
Critical Software, Coimbra, Portugal

Date: Thursday, April 11th, 2025

Abstract: The domains of railway and space systems both demand high levels of dependability and safety, yet they face unique challenges and adhere to different standards. This talk explores the application of dependability and safety principles in these two critical sectors, highlighting their specific challenges, commonalities, and differences. In the space domain, challenges include ensuring autonomy, safe communications, reconfigurations, long operational lifetimes, and the continuous availability of patch and dump functions. Additional concerns involve maintaining satellite battery charge, preventing system hangs or crashes, managing limited memory and processor resources, and detecting and correcting memory errors caused by single event upsets. Conversely, the railway domain focuses on passenger safety through rigorous and comprehensive hazard analysis, ensuring the operational readiness of emergency brakes, preventing unintended movements, controlling speed and signaling, and managing door operations, especially during transit. Both domains share commonalities such as the need for robust safety and dependability frameworks, though they follow different standards: ECSS and NASA standards for space, and CENELEC standards for railways. A key difference lies in certification requirements, with railways requiring certification and space systems not. Additionally, railways emphasize quantitative safety risk and hazard analysis, while space systems rely more on qualitative criticality analysis. This talk aims to provide insights into the distinct and overlapping aspects of dependability and safety in railway and space systems, offering a comprehensive understanding of their respective methodologies and practices.

Nuno Silva
Nuno Silva is the Safety Manager for aerospace and transportation projects at Critical Software, specializing in Safety, Verification, Validation, and RAMS. He graduated in Computer Engineering from École Polytechnique of Montreal University in 1997, with a focus on Robotics and Artificial Intelligence. Fluent in Portuguese, French Canadian, English, and Spanish, Nuno has extensive experience in research, training, management, specification, design, implementation, verification, and validation since 1997. He has worked in the financial (NBS Technologies), telecom (Motorola), and aerospace and transportation sectors (Critical Software). At Critical Software, Nuno has developed satellite data processing applications, conducted independent verification and validation of critical systems, and performed safety and quality assessments. He has managed numerous safety-critical projects, particularly in the railway sector, involving verification, validation, RAMS, qualification, and certification tasks.

Nuno holds a PhD from the University of Coimbra, combining industrial experience with research in Safety Critical Systems assessment and independent verification and validation. Since 2020, he has taught a Robust Software class in the Cybersecurity Master's program at the University of Aveiro.

Dr. Silva is well-versed in various international standards, including IEC, ECSS, NASA, and CENELEC, and has provided training on Safety Management and independent assessment activities. He has contributed to numerous peer-reviewed publications and collaborated with esteemed organizations such as ESA, NASA, JAXA, ESO, Thales, Bombardier, Motorola, and Airbus.