arXiv subjects

Simos Gerasimou

Publications and source records attributed to Simos Gerasimou.

At least 19 recordsLinked to original sources

arXiv2026

Leveraging System-Level Observations to Inform Bayesian Learning of Model Parameters for Quantitative Verification

Combining Bayesian learning and quantitative verification is a powerful toolset for analysing key quantitative properties of software systems, like reliability and response time. However, the accuracy and robustness of verification results strongly depend on the prior knowledge (PK) underlying Bayesian inference. This knowledge reflects original beliefs about the probability of events and typically depends on domain expertise. Using inaccurate or uninformative PK can negatively affect quantitative analysis, yielding incorrect verification results. Our EPIK approach tackles this important challenge by eliciting and embedding PK in quantitative verification equipped with Bayesian estimators. Unlike existing approaches that require PK on formal model transition parameters, EPIK leverages system-level properties that are directly observable and are linked to real-world semantics. EPIK formulates a twofold optimisation problem to derive the distributions of unknown transition parameters and then embeds these distributions to verify new or difficult-to-measure (elusive) properties. The detailed experimental evaluation using multiple variants of real-world case studies and diverse EPIK instantiations shows its effectiveness, flexibility and generality.

cs.SE↗

arXiv2026

Mind the Prompt: Self-adaptive Generation of Task Plan Explanations via LLMs

Integrating Large Language Models (LLMs) into complex software systems enables the generation of human-understandable explanations of opaque AI processes, such as automated task planning. However, the quality and reliability of these explanations heavily depend on effective prompt engineering. The lack of a systematic understanding of how diverse stakeholder groups formulate and refine prompts hinders the development of tools that can automate this process. We introduce COMPASS (COgnitive Modelling for Prompt Automated SynthesiS), a proof-of-concept self-adaptive approach that formalises prompt engineering as a cognitive and probabilistic decision-making process. COMPASS models unobservable users' latent cognitive states, such as attention and comprehension, uncertainty, and observable interaction cues as a POMDP, whose synthesised policy enables adaptive generation of explanations and prompt refinements. We evaluate COMPASS using two diverse cyber-physical system case studies to assess the adaptive explanation generation and their qualities, both quantitatively and qualitatively. Our results demonstrate the feasibility of COMPASS integrating human cognition and user profile's feedback into automated prompt synthesis in complex task planning systems.

cs.AI↗

arXiv2026

Formally Guaranteed Control Adaptation for ODD-Resilient Autonomous Systems

Ensuring reliable performance in situations outside the Operational Design Domain (ODD) remains a primary challenge in devising resilient autonomous systems. We explore this challenge by introducing an approach for adapting probabilistic system models to handle out-of-ODD scenarios while, in parallel, providing quantitative guarantees. Our approach dynamically extends the coverage of existing system situation capabilities, supporting the verification and adaptation of the system's behaviour under unanticipated situations. Preliminary results demonstrate that our approach effectively increases system reliability by adapting its behaviour and providing formal guarantees even under unforeseen out-of-ODD situations.

cs.LO↗

arXiv2025

Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows

Quantifying uncertainty in deep regression models is important both for understanding the confidence of the model and for safe decision-making in high-risk domains. Existing approaches that yield prediction intervals overlook distributional information, neglecting the effect of multimodal or asymmetric distributions on decision-making. Similarly, full or approximated Bayesian methods, while yielding the predictive posterior density, demand major modifications to the model architecture and retraining. We introduce MCNF, a novel post hoc uncertainty quantification method that produces both prediction intervals and the full conditioned predictive distribution. MCNF operates on top of the underlying trained predictive model; thus, no predictive model retraining is needed. We provide experimental evidence that the MCNF-based uncertainty estimate is well calibrated, is competitive with state-of-the-art uncertainty quantification methods, and provides richer information for downstream decision-making tasks.

cs.LG↗

arXiv2025

Safe But Not Sorry: Reducing Over-Conservatism in Safety Critics via Uncertainty-Aware Modulation

Ensuring the safe exploration of reinforcement learning (RL) agents is critical for deployment in real-world systems. Yet existing approaches struggle to strike the right balance: methods that tightly enforce safety often cripple task performance, while those that prioritize reward leave safety constraints frequently violated, producing diffuse cost landscapes that flatten gradients and stall policy improvement. We introduce the Uncertain Safety Critic (USC), a novel approach that integrates uncertainty-aware modulation and refinement into critic training. By concentrating conservatism in uncertain and costly regions while preserving sharp gradients in safe areas, USC enables policies to achieve effective reward-safety trade-offs. Extensive experiments show that USC reduces safety violations by approximately 40% while maintaining competitive or higher rewards, and reduces the error between predicted and true cost gradients by approximately 83%, breaking the prevailing trade-off between safety and performance and paving the way for scalable safe RL.

cs.LG↗

arXiv2025

Learning to Navigate Under Imperfect Perception: Conformalised Segmentation for Safe Reinforcement Learning

Reliable navigation in safety-critical environments requires both accurate hazard perception and principled uncertainty handling to strengthen downstream safety handling. Despite the effectiveness of existing approaches, they assume perfect hazard detection capabilities, while uncertainty-aware perception approaches lack finite-sample guarantees. We present COPPOL, a conformal-driven perception-to-policy learning approach that integrates distribution-free, finite-sample safety guarantees into semantic segmentation, yielding calibrated hazard maps with rigorous bounds for missed detections. These maps induce risk-aware cost fields for downstream RL planning. Across two satellite-derived benchmarks, COPPOL increases hazard coverage (up to 6x) compared to comparative baselines, achieving near-complete detection of unsafe regions while reducing hazardous violations during navigation (up to approx 50%). More importantly, our approach remains robust to distributional shift, preserving both safety and efficiency.

cs.LG↗

arXiv2025

Guided Uncertainty Learning Using a Post-Hoc Evidential Meta-Model

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 reshape predictions, without teaching the model when to be uncertain. We introduce GUIDE, a lightweight evidential learning meta-model approach that attaches to a frozen deep learning model and explicitly learns how and when to be uncertain. GUIDE identifies salient internal features via a calibration stage, and then employs these features to construct a noise-driven curriculum that teaches the model how and when to express uncertainty. GUIDE requires no retraining, no architectural modifications, and no manual intermediate-layer selection to the base deep learning model, thus ensuring broad applicability and minimal user intervention. The resulting model avoids distilling overconfidence from the base model, improves out-of-distribution detection by ~77% and adversarial attack detection by ~80%, while preserving in-distribution performance. Across diverse benchmarks, GUIDE consistently outperforms state-of-the-art approaches, evidencing the need for actively guiding uncertainty to close the gap between predictive confidence and reliability.

cs.LG↗

arXiv2025

Accelerating Policy Synthesis in Large-Scale MDPs via Hierarchical Adaptive Refinement

Software-intensive systems, such as software product lines and robotics, utilise Markov decision processes (MDPs) to capture uncertainty and analyse sequential decision-making problems. Despite the usefulness of conventional policy synthesis methods, they fail to scale to large state spaces. Our approach addresses this issue and accelerates policy synthesis in large MDPs by dynamically refining the MDP and iteratively selecting the most fragile MDP regions for refinement. This iterative procedure offers a balance between accuracy and efficiency, as refinement occurs only when necessary. We formally show that the composed policy is near-optimal under standard assumptions, with error bounded by the local solver tolerance and boundary mismatch. Across diverse case studies and MDPs up to 1M states, we demonstrate that our approach achieves up to $2\times$ speedup over PRISM, offering a competitive solution for real-world policy synthesis in large MDPs.

cs.AI↗

arXiv2025

Robust Adversarial Quantification via Conflict-Aware Evidential Deep Learning

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 quantification, models predictions as Dirichlet distributions of a single forward pass. However, EDL is particularly vulnerable to adversarially perturbed inputs, making overconfident errors. Conflict-aware Evidential Deep Learning (C-EDL) is a lightweight post-hoc uncertainty quantification approach that mitigates these issues, enhancing adversarial and OOD robustness without retraining. C-EDL generates diverse, task-preserving transformations per input and quantifies representational disagreement to calibrate uncertainty estimates when needed. C-EDL's conflict-aware prediction adjustment improves detection of OOD and adversarial inputs, maintaining high in-distribution accuracy and low computational overhead. Our experimental evaluation shows that C-EDL significantly outperforms state-of-the-art EDL variants and competitive baselines, achieving substantial reductions in coverage for OOD data (up to $\approx$55%) and adversarial data (up to $\approx$90%), across a range of datasets, attack types, and uncertainty metrics.

cs.LG↗

arXiv2025

Adaptive Human-Robot Collaborative Missions using Hybrid Task Planning

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 classes of constraints and uncertainties, its applicability is confined to relatively simple problems that can be comfortably addressed by the underpinning mathematically-based or heuristic-driven solver engines. In this paper, we introduce a hybrid approach that effectively solves the task planning problem by decomposing it into two intertwined parts, starting with the identification of a feasible plan and followed by its uncertainty augmentation and verification yielding a set of Pareto optimal plans. To enhance its robustness, adaptation tactics are devised for the evolving system requirements and agents' capabilities. We demonstrate our approach through an industrial case study involving workers and robots undertaking activities within a vineyard, showcasing the benefits of our hybrid approach both in the generation of feasible solutions and scalability compared to native planners.

cs.MA↗

arXiv2025

Verification and External Parameter Inference for Stochastic World Models

Given its ability to analyse stochastic models ranging from discrete and continuous-time Markov chains to Markov decision processes and stochastic games, probabilistic model checking (PMC) is widely used to verify system dependability and performance properties. However, modelling the behaviour of, and verifying these properties for many software-intensive systems requires the joint analysis of multiple interdependent stochastic models of different types, which existing PMC techniques and tools cannot handle. To address this limitation, we introduce a tool-supported UniversaL stochasTIc Modelling, verificAtion and synThEsis (ULTIMATE) framework that supports the representation, verification and synthesis of heterogeneous multi-model stochastic systems with complex model interdependencies. Through its unique integration of multiple PMC paradigms, and underpinned by a novel verification method for handling model interdependencies, ULTIMATE unifies-for the first time-the modelling of probabilistic and nondeterministic uncertainty, discrete and continuous time, partial observability, and the use of both Bayesian and frequentist inference to exploit domain knowledge and data about the modelled system and its context. A comprehensive suite of case studies and experiments confirm the generality and effectiveness of our novel verification framework.

cs.LO↗

arXiv2024

Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding

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 in unknown, black-box environments presents an even greater safety risk. We introduce ADVICE (Adaptive Shielding with a Contrastive Autoencoder), a novel post-shielding technique that distinguishes safe and unsafe features of state-action pairs during training, and uses this knowledge to protect the RL agent from executing actions that yield likely hazardous outcomes. Our comprehensive experimental evaluation against state-of-the-art safe RL exploration techniques shows that ADVICE significantly reduces safety violations (approx 50%) during training, with a competitive outcome reward compared to other techniques.

cs.AI↗

arXiv2024

Tree-Based versus Hybrid Graphical-Textual Model Editors: An Empirical Study of Testing Specifications

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 capture high-level domain concepts graphically and low-level domain details textually. We conducted an empirical user study with 22 participants to evaluate the implicit assumption of system modellers that hybrid notations are superior, and to investigate the tradeoffs between the default EMF-based tree model editor and a Sirius/Xtext-based hybrid model editor. The results of the user study indicate that users largely prefer the hybrid editor and are more confident with hybrid notations for understanding the meaning of conditions. Furthermore, we found that the tree editor provided superior performance for analysing ordered lists of model elements, whereas activities requiring the comprehension or modelling of complex conditions were carried out faster through the hybrid editor.

cs.SE↗

arXiv2024

DeepKnowledge: Generalisation-Driven Deep Learning Testing

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 systematic testing approaches that assess the DNN's capability to generalise and operate comparably beyond data in their training distribution. We address this gap with DeepKnowledge, a systematic testing methodology for DNN-based systems founded on the theory of knowledge generalisation, which aims to enhance DNN robustness and reduce the residual risk of 'black box' models. Conforming to this theory, DeepKnowledge posits that core computational DNN units, termed Transfer Knowledge neurons, can generalise under domain shift. DeepKnowledge provides an objective confidence measurement on testing activities of DNN given data distribution shifts and uses this information to instrument a generalisation-informed test adequacy criterion to check the transfer knowledge capacity of a test set. Our empirical evaluation of several DNNs, across multiple datasets and state-of-the-art adversarial generation techniques demonstrates the usefulness and effectiveness of DeepKnowledge and its ability to support the engineering of more dependable DNNs. We report improvements of up to 10 percentage points over state-of-the-art coverage criteria for detecting adversarial attacks on several benchmarks, including MNIST, SVHN, and CIFAR.

cs.LG↗

arXiv2024

Quantitative Assurance and Synthesis of Controllers from Activity Diagrams

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 verifying them require domain knowledge. This makes it not accessible for researchers and engineers who may not have the required knowledge. Previous studies have extended UML activity diagrams (ADs), developed transformations, and implemented accompanying tools for automation. The research, however, is incomprehensive and not fully open, which makes it hard to be evaluated, extended, adapted, and accessed. In this paper, we propose a comprehensive verification framework for ADs, including a new profile for probability, time, and quality annotations, a semantics interpretation of ADs in three Markov models, and a set of transformation rules from activity diagrams to the PRISM language, supported by PRISM and Storm. Most importantly, we developed algorithms for transformation and implemented them in a tool, called QASCAD, using model-based techniques, for fully automated verification. We evaluated one case study where multiple robots are used for delivery in a hospital and further evaluated six other examples from the literature. With all these together, this work makes noteworthy contributions to the verification of ADs by improving evaluation, extensibility, adaptability, and accessibility.

cs.LO↗

arXiv2023

Robust Uncertainty Quantification Using Conformalised Monte Carlo Prediction

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's confidence per prediction, informing decision-making by considering the effect of randomness and model misspecification. Despite the advances of state-of-the-art UQ methods, they are computationally expensive or produce conservative prediction sets/intervals. We introduce MC-CP, a novel hybrid UQ method that combines a new adaptive Monte Carlo (MC) dropout method with conformal prediction (CP). MC-CP adaptively modulates the traditional MC dropout at runtime to save memory and computation resources, enabling predictions to be consumed by CP, yielding robust prediction sets/intervals. Throughout comprehensive experiments, we show that MC-CP delivers significant improvements over advanced UQ methods, like MC dropout, RAPS and CQR, both in classification and regression benchmarks. MC-CP can be easily added to existing models, making its deployment simple.

cs.LG↗

arXiv2023

Bayesian Learning for the Robust Verification of Autonomous Robots

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 missions safely and effectively. Here we present a Bayesian learning framework that enables this runtime verification of autonomous robots. The framework uses prior knowledge and observations of the verified robot to learn expected ranges for the occurrence rates of regular and singular (e.g., catastrophic failure) events. Interval continuous-time Markov models defined using these ranges are then analysed to obtain expected intervals of variation for system properties such as mission duration and success probability. We apply the framework to an autonomous robotic mission for underwater infrastructure inspection and repair. The formal proofs and experiments presented in the paper show that our framework produces results that reflect the uncertainty intrinsic to many real-world systems, enabling the robust verification of their quantitative properties under parametric uncertainty.

cs.RO↗

arXiv2022

Software Performability Analysis Using Fast Parametric Model Checking

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 decomposing a parametric discrete-time Markov chain (pDTMC) model of the software system under verification into fragments that can be analysed independently, yielding results that are then combined to establish the required software performability properties. Our fast parametric model checking (fPMC) technique enables the formal analysis of software systems modelled by pDTMCs that are too complex to be handled by existing PMC methods. Furthermore, for many pDTMCs that state-of-the-art parametric model checkers can analyse, fPMC produces solutions (i.e., algebraic formulae) that are simpler and much faster to evaluate. We show experimentally that adding fPMC to the existing repertoire of PMC methods improves the efficiency of parametric model checking significantly, and extends its applicability to software systems with more complex behaviour than currently possible.

cs.LO↗