Simos Gerasimou
YOU?
Author Swipe
Guided Uncertainty Learning Using a Post-Hoc Evidential Meta-Model Open
Reliable uncertainty quantification remains a major obstacle to the deployment of deep learning models under distributional shift. Existing post-hoc approaches that retrofit pretrained models either inherit misplaced confidence or merely r…
Quantifying Adversarial Uncertainty in Evidential Deep Learning using Conflict Resolution Open
Reliability of deep learning models is critical for deployment in high-stakes applications, where out-of-distribution or adversarial inputs may lead to detrimental outcomes. Evidential Deep Learning, an efficient paradigm for uncertainty q…
View article: Adaptive Human-Robot Collaborative Missions using Hybrid Task Planning
Adaptive Human-Robot Collaborative Missions using Hybrid Task Planning Open
Producing robust task plans in human-robot collaborative missions is a critical activity in order to increase the likelihood of these missions completing successfully. Despite the broad research body in the area, which considers different …
View article: Code-Level Safety Verification for Automated Driving: A Case Study
Code-Level Safety Verification for Automated Driving: A Case Study Open
The formal safety analysis of automated driving vehicles poses unique challenges due to their dynamic operating conditions and significant complexity. This paper presents a case study of applying formal safety verification to adaptive crui…
View article: Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding
Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding Open
Empowering safe exploration of reinforcement learning (RL) agents during training is a critical challenge towards their deployment in many real-world scenarios. When prior knowledge of the domain or task is unavailable, training RL agents …
View article: Uncertainty Flow Diagrams: Towards a Systematic Representation of Uncertainty Propagation and Interaction in Adaptive Systems
Uncertainty Flow Diagrams: Towards a Systematic Representation of Uncertainty Propagation and Interaction in Adaptive Systems Open
Sources of uncertainty in adaptive systems are rarely independent, and their interaction can affect the attainment of system goals in unpredictable ways. Despite ample work on “taming” uncertainty, the research community has devoted little…
Tree-Based versus Hybrid Graphical-Textual Model Editors: An Empirical Study of Testing Specifications Open
Tree-based model editors and hybrid graphical-textual model editors have advantages and limitations when editing domain models. Data is displayed hierarchically in tree-based model editors, whereas hybrid graphical-textual model editors ca…
DeepKnowledge: Generalisation-Driven Deep Learning Testing Open
Despite their unprecedented success, DNNs are notoriously fragile to small shifts in data distribution, demanding effective testing techniques that can assess their dependability. Despite recent advances in DNN testing, there is a lack of …
View article: Robust Uncertainty Quantification Using Conformalised Monte Carlo Prediction
Robust Uncertainty Quantification Using Conformalised Monte Carlo Prediction Open
Deploying deep learning models in safety-critical applications remains a very challenging task, mandating the provision of assurances for the dependable operation of these models. Uncertainty quantification (UQ) methods estimate the model’…
Quantitative Assurance and Synthesis of Controllers from Activity Diagrams Open
Probabilistic model checking is a widely used formal verification technique to automatically verify qualitative and quantitative properties for probabilistic models. However, capturing such systems, writing corresponding properties, and ve…
View article: Towards a Research Agenda for Understanding and Managing Uncertainty in Self-Adaptive Systems
Towards a Research Agenda for Understanding and Managing Uncertainty in Self-Adaptive Systems Open
Despite considerable research efforts on handling uncertainty in self-adaptive systems, a comprehensive understanding of the precise nature of uncertainty is still lacking. This paper summarises the findings of the 2023 Bertinoro Seminar o…
Semantic Data Augmentation for Deep Learning Testing Using Generative AI Open
he performance of state-of-the-art Deep Learning models heavily depends on the availability of well-curated training and testing datasets that sufficiently capture the operational domain. Data augmentation is an effective technique in alle…
Robust Uncertainty Quantification Using Conformalised Monte Carlo Prediction Open
Deploying deep learning models in safety-critical applications remains a very challenging task, mandating the provision of assurances for the dependable operation of these models. Uncertainty quantification (UQ) methods estimate the model'…
View article: Bayesian Learning for the Robust Verification of Autonomous Robots
Bayesian Learning for the Robust Verification of Autonomous Robots Open
Autonomous robots used in infrastructure inspection, space exploration and other critical missions operate in highly dynamic environments. As such, they must continually verify their ability to complete the tasks associated with these miss…
View article: Probabilistic program performance analysis with confidence intervals
Probabilistic program performance analysis with confidence intervals Open
More often than not, the algorithms implemented by software systems continue to operate correctly when executed on different platforms or with different inputs, and can be easily replaced with functionally equivalent ones. However, such ch…
Model-driven design space exploration for multi-robot systems in simulation Open
Multi-robot systems are increasingly deployed to provide services and accomplish missions whose complexity or cost is too high for a single robot to achieve on its own. Although multi-robot systems offer increased reliability via redundanc…
Software Performability Analysis Using Fast Parametric Model Checking Open
We present an efficient parametric model checking (PMC) technique for the analysis of software performability, i.e., of the performance and dependability properties of software systems. The new PMC technique works by automatically decompos…
SORA Methodology for Multi-UAS Airframe Inspections in an Airport Open
Deploying Unmanned Aircraft Systems (UAS) in safety- and business-critical operations requires demonstrating compliance with applicable regulations and a comprehensive understanding of the residual risk associated with the UAS operation. T…
Fast Parametric Model Checking through Model Fragmentation Open
Parametric model checking (PMC) computes algebraic formulae that express key non-functional properties of a system (reliability, performance, etc.) as rational functions of the system and environment parameters. In software engineering, PM…
Intelligent Run-Time Partitioning of Low-Code System Models Open
Over the last 2 decades, several dedicated languages have been proposed to support model management activities such as model validation, transformation, and code generation. As software systems become more complex, underlying system models…
Intelligent run-time partitioning of low-code system models Open
International audience
Supporting robotic software migration using static analysis and model-driven engineering Open
The wide use of robotic systems contributed to developing robotic software highly coupled to the hardware platform running the robotic system. Due to increased maintenance cost or changing business priorities, the robotic hardware is infre…
Genetic Improvement @ ICSE 2020 Open
Following Prof. Mark Harman of Facebook's keynote and formal presentations (which are recorded in the proceed- ings) there was a wide ranging discussion at the eighth inter- national Genetic Improvement workshop, GI-2020 @ ICSE (held as pa…
Automatic generation of UML profile graphical editors for Papyrus Open
UML profiles offer an intuitive way for developers to build domain-specific modelling languages by reusing and extending UML concepts. Eclipse Papyrus is a powerful open-source UML modelling tool which supports UML profiling. However, with…
View article: Learning to Learn in Collective Adaptive Systems: Mining Design Patterns for Data-driven Reasoning
Learning to Learn in Collective Adaptive Systems: Mining Design Patterns for Data-driven Reasoning Open
Engineering collective adaptive systems (CAS) with learning capabilities is a challenging task due to their multi-dimensional and complex design space. Data-driven approaches for CAS design could introduce new insights enabling system engi…
Genetic Improvement @ ICSE 2020 Open
Following Prof. Mark Harman of Facebook's keynote and formal presentations (which are recorded in the proceedings) there was a wide ranging discussion at the eighth international Genetic Improvement workshop, GI-2020 @ ICSE (held as part o…
Importance-Driven Deep Learning System Testing Open
Deep Learning (DL) systems are key enablers for engineering intelligent applications due to their ability to solve complex tasks such as image recognition and machine translation. Nevertheless, using DL systems in safety- and security-crit…