Related papers: The Missing Variable: Socio-Technical Alignment in…
Collaborative AI systems aim at working together with humans in a shared space to achieve a common goal. This setting imposes potentially hazardous circumstances due to contacts that could harm human beings. Thus, building such systems with…
As AI systems become embedded in everyday practice, value misalignment has emerged as a pressing concern. Yet, dominant alignment approaches remain model centric, treating users as passive recipients of prespecified values rather than as…
Artificial intelligence now decides who receives a loan, who is flagged for criminal investigation, and whether an autonomous vehicle brakes in time. Governments have responded: the EU AI Act, the NIST Risk Management Framework, and the…
Embedding artificial intelligence into systems introduces significant challenges to modern engineering practices. Hazard analysis tools and processes have not yet been adequately adapted to the new paradigm. This paper describes initial…
The accelerating deployment of artificial intelligence systems across regulated sectors has exposed critical fragmentation in risk assessment methodologies. A significant "language barrier" currently separates technical security teams, who…
Artificial Intelligence (AI) is reshaping many societal domains, raising critical questions about its risks, benefits, and the potential misalignment between public and academic perspectives. This study examines how the general public…
Frontier AI Safety Policies concentrate on prevention: capability evaluations, deployment gates, and usage constraints, while neglecting the capacity to coordinate responses when prevention fails. We argue this coordination gap is…
The maintained artifact in an AI-enabled system is not code plus settings, but a versioned governed program space: domains, structural constraints, eligibility, evaluation assets, and a statistical release gate. AI-enabled systems operate…
As artificial intelligence (AI) reshapes industries and societies, ensuring its trustworthiness-through mitigating ethical risks like bias, opacity, and accountability deficits-remains a global challenge. International Organization for…
AI systems comprise a range of interactions across the technical and organisational components of a range of actors. These components work together to provide the systems' functionality. This socio-technical assemblage is increasingly…
With the advent of AI technologies, humans and robots are increasingly teaming up to perform collaborative tasks. To enable smooth and effective collaboration, the topic of value alignment (operationalized herein as the degree of dynamic…
Although general-purpose AI systems offer transformational opportunities in science and industry, they simultaneously raise critical concerns about safety, misuse, and potential loss of control. Despite these risks, methods for assessing…
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…
As AI systems increasingly influence critical decisions, they face threats that exploit reasoning mechanisms rather than technical infrastructure. We present a framework for cognitive cybersecurity, a systematic protection of AI reasoning…
All of the frontier AI companies have published safety frameworks where they define capability thresholds and risk mitigations that determine how they will safely develop and deploy their models. Adoption of systematic approaches to risk…
AI systems face a growing number of AI security threats that are increasingly exploited in the real world. Hence, shared AI incident reporting practices are emerging in industry as best practice and as mandated by regulatory requirements.…
The advent of advanced AI underscores the urgent need for comprehensive safety evaluations, necessitating collaboration across communities (i.e., AI, software engineering, and governance). However, divergent practices and terminologies…
Prior work on trustworthy AI emphasizes model-internal properties such as bias mitigation, adversarial robustness, and interpretability. As AI systems evolve into autonomous agents deployed in open environments and increasingly connected to…
AI safety practitioners invest considerable resources in AI system evaluations, but these investments may be wasted if evaluations fail to realize their impact. This paper questions the core value proposition of evaluations: that they…
AI safety benchmarks are pivotal for safety in advanced AI systems; however, they have significant technical, epistemic, and sociotechnical shortcomings. We present a review of 210 safety benchmarks that maps out common challenges in safety…