Related papers: Failure divergence refinement for Event-B

Starting from two case histories, where only after thorough Failure Analysis the suddenly appearance of a failure was linked to much earlier events, the possibility of improving the reliability and of adjusting the reliability prediction…

Deep learning models for survival analysis have gained significant attention in the literature, but they suffer from severe performance deficits when the dataset contains many irrelevant features. We give empirical evidence for this problem…

The role played by counterexamples in standard system analysis is well known; but less common is a notion of counterexample in probabilistic systems refinement. In this paper we extend previous work using counterexamples to inductive…

Event-B has been actively used within the EU Deploy project to model dependable systems from various application domains. As a result, we have created a number of formal approaches to explicitly reason about dependability in the refinement…

Data-driven models, especially deep learning classifiers often demonstrate great success on clean datasets. Yet, they remain vulnerable to common data distortions such as adversarial and common corruption perturbations. These perturbations…

Many recent works have proposed methods to train classifiers with local robustness properties, which can provably eliminate classes of evasion attacks for most inputs, but not all inputs. Since data distribution shift is very common in…

Deep neural networks (DNNs) are widely used in real-world applications, yet they remain vulnerable to errors and adversarial attacks. Formal verification offers a systematic approach to identify and mitigate these vulnerabilities, enhancing…

Benchmarks measure whether a model is correct. They do not measure whether a model is reliable. This distinction is largely academic for single-shot inference, but becomes critical for agentic AI systems, where a single rephrased prompt can…

Automated verification has become an essential part in the security evaluation of cryptographic protocols. In this context privacy-type properties are often modelled by indistinguishability statements, expressed as behavioural equivalences…

This article studies how to detect and explain concept drift. Human activity recognition is used as a case study together with a online batch learning situation where the quality of the labels used in the model updating process starts to…

This paper discusses highly general mechanisms for specifying the refinement of a real-time system as a collection of lower level parallel components that preserve the timing and functional requirements of the upper level specification.…

Among the three main components (data, labels, and models) of any supervised learning system, data and models have been the main subjects of active research. However, studying labels and their properties has received very little attention.…

Software verification is a tedious process that involves the analysis of multiple failed verification attempts, and adjustments of the program or specification. This is especially the case for complex requirements, e.g., regarding security…

Large pre-trained language models have shown remarkable performance over the past few years. These models, however, sometimes learn superficial features from the dataset and cannot generalize to the distributions that are dissimilar to the…

Event reconstruction is a fundamental part of the digital forensic process, helping to answer key questions like who, what, when, and how. A common way of accomplishing that is to use tools to create timelines, which are then analyzed.…

In this paper, we focus on improving the online face liveness detection system to enhance the security of the downstream face recognition system. Most of the existing frame-based methods are suffering from the prediction inconsistency…

Our scientific knowledge is increasingly built on software output. User code which defines data analysis pipelines and computational models is essential for research in the natural and social sciences, but little is known about how to…

Feature selection has attracted significant attention in data mining and machine learning in the past decades. Many existing feature selection methods eliminate redundancy by measuring pairwise inter-correlation of features, whereas the…

Stepwise refinement and Design-by-Contract are two formal approaches for modelling systems. These approaches are widely used in the development of systems. Both approaches have (dis-)advantages. This thesis aims to answer, is it possible to…

The Refl1d program is used for modeling and fitting data from neutron and X-ray reflectometry experiments. The model of the (thin-film) samples is typically constructed of discrete layers of different scattering-length densities (SLD).…