Related papers: SETA: Statistical Fault Attribution for Compound A…

Adversarial robustness is one of the essential safety criteria for guaranteeing the reliability of machine learning models. While various adversarial robustness testing approaches were introduced in the last decade, we note that most of…

The systematic assessment of AI systems is increasingly vital as these technologies enter high-stakes domains. To address this, the EU's Artificial Intelligence Act introduces AI Regulatory Sandboxes (AIRS): supervised environments where AI…

Fault diagnosis is crucial for complex autonomous mobile systems, especially for modern-day autonomous driving (AD). Different actors, numerous use cases, and complex heterogeneous components motivate a fault diagnosis of the system and…

Interpretability of Deep Learning (DL) is a barrier to trustworthy AI. Despite great efforts made by the Explainable AI (XAI) community, explanations lack robustness -- indistinguishable input perturbations may lead to different XAI…

In recent years, there has been significant attention given to the robustness assessment of neural networks. Robustness plays a critical role in ensuring reliable operation of artificial intelligence (AI) systems in complex and uncertain…

We introduce a grey-box conformance testing method for networks of interconnected Mealy Machines. This approach addresses the scenario where all interfaces of the component under test are observable, but its inputs are under the control of…

Reliable and robust evaluation methods are a necessary first step towards developing machine learning models that are themselves robust and reliable. Unfortunately, current evaluation protocols typically used to assess classifiers fail to…

Audits contribute to the trustworthiness of Learning Analytics (LA) systems that integrate Artificial Intelligence (AI) and may be legally required in the future. We argue that the efficacy of an audit depends on the auditability of the…

Artificial intelligence (AI) systems have become increasingly popular in many areas. Nevertheless, AI technologies are still in their developing stages, and many issues need to be addressed. Among those, the reliability of AI systems needs…

Artificial intelligence develops techniques and systems whose performance must be evaluated on a regular basis in order to certify and foster progress in the discipline. We will describe and critically assess the different ways AI systems…

With the advancements in machine learning (ML) methods and compute resources, artificial intelligence (AI) empowered systems are becoming a prevailing technology. However, current AI technology such as deep learning is not flawless. The…

While deep learning models have greatly improved the performance of most artificial intelligence tasks, they are often criticized to be untrustworthy due to the black-box problem. Consequently, many works have been proposed to study the…

This paper presents for the first time, to our knowledge, a framework for verifying neural network behavior in power system applications. Up to this moment, neural networks have been applied in power systems as a black-box; this has…

Ensembling certifiably robust neural networks is a promising approach for improving the \emph{certified robust accuracy} of neural models. Black-box ensembles that assume only query-access to the constituent models (and their robustness…

Deep learning models for medical image segmentation and object detection are becoming increasingly available as clinical products. However, as details are rarely provided about the training data, models may unexpectedly fail when cases…

In safety-critical deep learning applications, robustness measures the ability of neural models that handle imperceptible perturbations in input data, which may lead to potential safety hazards. Existing pre-deployment robustness assessment…

Robustness in deep neural networks and machine learning algorithms in general is an open research challenge. In particular, it is difficult to ensure algorithmic performance is maintained on out-of-distribution inputs or anomalous instances…

Most AI benchmarks saturate within years or even months after they are introduced, making it hard to study long-run trends in AI capabilities. To address this challenge, we build a statistical framework that stitches benchmarks together,…

Automata extraction is a method for synthesising interpretable surrogates for black-box neural models that can be analysed symbolically. Existing techniques assume a finite input alphabet, and thus are not directly applicable to data…

State-of-the-art NLP models can often be fooled by human-unaware transformations such as synonymous word substitution. For security reasons, it is of critical importance to develop models with certified robustness that can provably…