Related papers: Bounding the Black Box: A Statistical Certificatio…
As artificial intelligence (AI) technologies increasingly enter important sectors like healthcare, transportation, and finance, the development of effective governance frameworks is crucial for dealing with ethical, security, and societal…
"Safety" and "Risk" are key concepts for the design and development of automated vehicles. For the market introduction or large-scale field tests, both concepts are not only relevant for engineers developing the vehicles, but for all…
The deployment of AI systems faces three critical governance challenges that current frameworks fail to adequately address. First, organizations struggle with inadequate risk assessment at the use case level, exemplified by the Humana class…
The EU Artificial Intelligence Act (AIA) establishes different legal principles for different types of AI systems. While prior work has sought to clarify some of these principles, little attention has been paid to robustness and…
There is an increasing adoption of artificial intelligence in safety-critical applications, yet practical schemes for certifying that AI systems are safe, lawful and socially acceptable remain scarce. This white paper presents the T\"UV…
The rapid development of artificial intelligence (AI) has led to increasing concerns about the capability of AI systems to make decisions and behave responsibly. Responsible AI (RAI) refers to the development and use of AI systems that…
Despite large progress in Explainable and Safe AI, practitioners suffer from a lack of regulation and standards for AI safety. In this work we merge recent regulation efforts by the European Union and first proposals for AI guidelines with…
Artificial intelligence-based systems for player risk detection have become central to harm prevention efforts in the gambling industry. However, growing concerns around transparency and effectiveness have highlighted the absence of…
The European Union's AI Act represents a crucial step towards regulating ethical and responsible AI systems. However, we find an absence of quantifiable fairness metrics and the ambiguity in terminology, particularly the interchangeable use…
Modern AI technologies enable autonomous vehicles to perceive complex scenes, predict human behavior, and make real-time driving decisions. However, these data-driven components often operate as black boxes, lacking interpretability and…
AI-controlled robotic systems pose a risk to human workers and the environment. Classical risk assessment methods cannot adequately describe such black box systems. Therefore, new methods for a dynamic risk assessment of such AI-controlled…
Artificial Intelligence (AI) systems are increasingly deployed in legal contexts, where their opacity raises significant challenges for fairness, accountability, and trust. The so-called ``black box problem'' undermines the legitimacy of…
As AI rapidly advances, the security risks posed by AI are becoming increasingly severe, especially in critical scenarios, including those posing existential risks. If AI becomes uncontrollable, manipulated, or actively evades safety…
In the future, AI will increasingly find its way into systems that can potentially cause physical harm to humans. For such safety-critical systems, it must be demonstrated that their residual risk does not exceed what is acceptable. This…
Art. 50 II of the EU Artificial Intelligence Act mandates dual transparency for AI-generated content: outputs must be labeled in both human-understandable and machine-readable form for automated verification. This requirement, entering into…
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…
Autonomous systems use independent decision-making with only limited human intervention to accomplish goals in complex and unpredictable environments. As the autonomy technologies that underpin them continue to advance, these systems will…
Given a black-box AI system and a task, at what confidence level can a practitioner trust the system's output? We answer with a reliability level -- a single number per system-task pair, derived from self-consistency sampling and conformal…
The rapid advancement and deployment of AI systems have created an urgent need for standard safety-evaluation frameworks. This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product…
AI is poised to revolutionize telecommunication networks by boosting efficiency, automation, and decision-making. However, the black-box nature of most AI models introduces substantial risk, possibly deterring adoption by network operators.…