Related papers: If a Human Can See It, So Should Your System: Reli…

Safety-critical Autonomous Systems require trustworthy and transparent decision-making process to be deployable in the real world. The advancement of Machine Learning introduces high performance but largely through black-box algorithms. We…

Predictive safety filters enable the integration of potentially unsafe learning-based control approaches and humans into safety-critical systems. In addition to simple constraint satisfaction, many control problems involve additional…

Visual reasoning is central to human cognition, enabling individuals to interpret and abstractly understand their environment. Although recent Multimodal Large Language Models (MLLMs) have demonstrated impressive performance across language…

Scientific machine learning (SciML) models are transforming many scientific disciplines. However, the development of good modeling practices to increase the trustworthiness of SciML has lagged behind its application, limiting its potential…

Being able to assess the confidence of individual predictions in machine learning models is crucial for decision making scenarios. Specially, in critical applications such as medical diagnosis, security, and unmanned vehicles, to name a…

As deep neural networks (DNNs) get adopted in an ever-increasing number of applications, explainability has emerged as a crucial desideratum for these models. In many real-world tasks, one of the principal reasons for requiring…

Trustworthy machine learning is driving a large number of ML community works in order to improve ML acceptance and adoption. The main aspect of trustworthy machine learning are the followings: fairness, uncertainty, robustness,…

Machine Learning (ML) is now used in a range of systems with results that are reported to exceed, under certain conditions, human performance. Many of these systems, in domains such as healthcare , automotive and manufacturing, exhibit high…

Vision language models (VLMs) are designed to extract relevant visuospatial information from images. Some research suggests that VLMs can exhibit humanlike scene understanding, while other investigations reveal difficulties in their ability…

Multimedia event detection is the task of detecting a specific event of interest in an user-generated video on websites. The most fundamental challenge facing this task lies in the enormously varying quality of the video as well as the…

There is a strong consensus that combining the versatility of machine learning with the assurances given by formal verification is highly desirable. It is much less clear what verified machine learning should mean exactly. We consider this…

The increasing adoption of machine learning tools has led to calls for accountability via model interpretability. But what does it mean for a machine learning model to be interpretable by humans, and how can this be assessed? We focus on…

Context: Machine Learning (ML) has been at the heart of many innovations over the past years. However, including it in so-called 'safety-critical' systems such as automotive or aeronautic has proven to be very challenging, since the shift…

Critical systems, such as those used in healthcare, defence, and disaster management, demand rigorous requirements engineering to ensure safety and reliability. Yet, much of this rigour has traditionally focused on technical assurance,…

Reproducibility of modeling is a problem that exists for any machine learning practitioner, whether in industry or academia. The consequences of an irreproducible model can include significant financial costs, lost time, and even loss of…

The accurate prediction of danger levels in video content is critical for enhancing safety and security systems, particularly in environments where quick and reliable assessments are essential. In this study, we perform a comparative…

The rapidly developing AI systems and applications still require human involvement in practically all parts of the analytics process. Human decisions are largely based on visualizations, providing data scientists details of data properties…

Lack of reliability is a well-known issue for reinforcement learning (RL) algorithms. This problem has gained increasing attention in recent years, and efforts to improve it have grown substantially. To aid RL researchers and production…

Recently, face recognition systems have demonstrated remarkable performances and thus gained a vital role in our daily life. They already surpass human face verification accountability in many scenarios. However, they lack explanations for…

Autonomous Driving Systems (ADS) use complex decision-making (DM) models with multimodal sensory inputs, making rigorous validation and verification (V&V) essential for safety and reliability. These models pose challenges in diagnosing…