Related papers: An AI System Evaluation Framework for Advancing AI…
AI systems are often introduced with high expectations, yet many fail to deliver, resulting in unintended harm and missed opportunities for benefit. We frequently observe significant "AI Mismatches", where the system's actual performance…
Ensuring and validating the safe operation of automated vehicles are key challenges for their market launch. Scenario-based development and test approaches are currently being pursued as possible solutions. An essential prerequisite for…
Disaggregated evaluations of AI systems, in which system performance is assessed and reported separately for different groups of people, are conceptually simple. However, their design involves a variety of choices. Some of these choices…
With an increasing degree of automation, automated vehicle systems become more complex in terms of functional components as well as interconnected hardware and software components. Thus, holistic systems engineering becomes a severe…
Conversational AI systems combine AI-based solutions with the flexibility of conversational interfaces. However, most existing testing solutions do not straightforwardly adapt to the characteristics of conversational interaction or to the…
As AI systems become more advanced, companies and regulators will make difficult decisions about whether it is safe to train and deploy them. To prepare for these decisions, we investigate how developers could make a 'safety case,' which is…
The popularisation of applying AI in businesses poses significant challenges relating to ethical principles, governance, and legal compliance. Although businesses have embedded AI into their day-to-day processes, they lack a unified…
Availability of powerful computation and communication technology as well as advances in artificial intelligence enable a new generation of complex, AI-intense systems and applications. Such systems and applications promise exciting…
Frontier AI systems are being adopted across Africa, yet most AI safety evaluations are designed and validated in Western environments. In this paper, we argue that the portability gap can leave Africa-centric pathways to severe harm…
AI is being increasingly used to aid response efforts to humanitarian emergencies at multiple levels of decision-making. Such AI systems are generally understood to be stand-alone tools for decision support, with ethical assessments,…
We present an automated crosswalk framework that compares an AI safety policy document pair under a shared taxonomy of activities. Using the activity categories defined in Activity Map on AI Safety as fixed aspects, the system extracts and…
The growing need for accountability of the people behind AI systems can be addressed by leveraging processes in three fields of study: ethics, law, and computer science. While these fields are often considered in isolation, they rely on…
Across academia, industry, and government, ``AI'' has become central in research and development, regulatory debates, and promises of ever faster and more capable decision-making and action. In numerous domains, especially safety-critical…
Embodied Artificial Intelligence (Embodied AI) integrates perception, cognition, planning, and interaction into agents that operate in open-world, safety-critical environments. As these systems gain autonomy and enter domains such as…
Artificial intelligence (AI) is rapidly transforming education, presenting unprecedented opportunities for personalized learning and streamlined content creation. However, realizing the full potential of AI in educational settings…
Equity Bias is a philosophical and practical framework for building smarter, more equitable AI systems. Grounded in hermeneutic philosophy and epistemic injustice theory, it treats bias not as an error to eliminate but as a reflection of…
The growing influence and decision-making capacities of Autonomous systems and Artificial Intelligence in our lives force us to consider the values embedded in these systems. But how ethics should be implemented into these systems? In this…
The design of embedded safety-critical systems such as those used in next-generation automotive and autonomous platforms, is increasingly challenged by escalating system complexity, hardware-software heterogeneity, and the integration of…
This document presents a preliminary compilation of general-purpose AI (GPAI) evaluation practices that may promote internal validity, external validity and reproducibility. It includes suggestions for human uplift studies and benchmark…
As frontier AI models become more capable, evaluating their potential to enable cyberattacks is crucial for ensuring the safe development of Artificial General Intelligence (AGI). Current cyber evaluation efforts are often ad-hoc, lacking…