Related papers: The Open-Box Fallacy: Why AI Deployment Needs a Ca…
Software Model Checkers have shown outstanding performance improvements in recent times. Moreover, for specific use cases, formal verification techniques have shown to be highly effective, leading to a number of high-profile success…
While Artificial Intelligence (AI) offers transformative potential for operational performance, its deployment in safety-critical domains such as aviation requires strict adherence to rigorous certification standards. Current EASA…
Artificial Intelligence (AI) has become an integral part of modern-day security solutions for its ability to learn very complex functions and handling "Big Data". However, the lack of explainability and interpretability of successful AI…
AI systems have been widely adopted across various domains in the real world. However, in high-value, sensitive, or safety-critical applications such as self-management for personalized health or food recommendation with a specific purpose…
Modern cloud-based AI training relies on extensive telemetry and logs to ensure accountability. While these audit trails enable retrospective inspection, they struggle to address the inherent non-determinism of deep learning. Stochastic…
Artificial Intelligence (AI) applications are being used to predict and assess behaviour in multiple domains, such as criminal justice and consumer finance, which directly affect human well-being. However, if AI is to improve people's…
The integration of artificial intelligence into business processes has significantly enhanced decision-making capabilities across various industries such as finance, healthcare, and retail. However, explaining the decisions made by these AI…
Decentralized AI systems, such as federated learning, can play a critical role in further unlocking AI asset marketplaces (e.g., healthcare data marketplaces) thanks to increased asset privacy protection. Unlocking this big potential…
Calibration is a frequently invoked concept when useful label probability estimates are required on top of classification accuracy. A calibrated model is a function whose values correctly reflect underlying label probabilities. Calibration…
Explainable Artificial Intelligence (XAI) has become popular in the last few years. The Artificial Intelligence (AI) community in general, and the Machine Learning (ML) community in particular, is coming to the realisation that in many…
Recent debates on artificial intelligence increasingly emphasise questions of AI consciousness and moral status, yet there remains little agreement on how such properties should be evaluated. In this paper, we argue that awareness offers a…
Today, AI is being increasingly used to help human experts make decisions in high-stakes scenarios. In these scenarios, full automation is often undesirable, not only due to the significance of the outcome, but also because human experts…
AI safety is still largely framed as alignment: training models to follow human preferences, safety policies, and normative constraints. That framing has improved the behavior of modern language models, but aligned behavior does not by…
Purpose: The introduction of artificial intelligence / machine learning (AI/ML) products to the regulated fields of pharmaceutical research and development (R&D) and drug manufacture, and medical devices (MD) and in-vitro diagnostics (IVD),…
A cautious interpretation of AI regulations and policy in the EU and the USA place explainability as a central deliverable of compliant AI systems. However, from a technical perspective, explainable AI (XAI) remains an elusive and complex…
AI systems have seen significant adoption in various domains. At the same time, further adoption in some domains is hindered by inability to fully trust an AI system that it will not harm a human. Besides the concerns for fairness, privacy,…
This paper claims that machine learning models deployed in high stakes domains such as medicine must be interpretable, shareable, reproducible and accountable. We argue that these principles should form the foundational design criteria for…
Most frameworks for assessing the openness of AI systems use narrow criteria such as availability of data, model, code, documentation, and licensing terms. However, to evaluate whether the intended effects of openness - such as…
Generative AI is entering research, education, and professional work faster than current governance frameworks can specify how AI-assisted outputs should be judged in learning-intensive settings. The central problem is proxy failure: a…
The lack of explainability of Artificial Intelligence (AI) is one of the first obstacles that the industry and regulators must overcome to mitigate the risks associated with the technology. The need for eXplainable AI (XAI) is evident in…