Related papers: Nuclear Arms Control Verification and Lessons for …
Developing and certifying safe - or so-called trustworthy - AI has become an increasingly salient issue, especially in light of upcoming regulation such as the EU AI Act. In this context, the black-box nature of machine learning models…
Assuring safety of artificial intelligence (AI) applied to safety-critical systems is of paramount importance. Especially since research in the field of automated driving shows that AI is able to outperform classical approaches, to handle…
Verified artificial intelligence (AI) is the goal of designing AI-based systems that that have strong, ideally provable, assurances of correctness with respect to mathematically-specified requirements. This paper considers Verified AI from…
What makes safety claims about general purpose AI systems such as large language models trustworthy? We show that rather than the capabilities of security tools such as alignment and red teaming procedures, it is security practices based on…
The malicious use or malfunction of advanced general-purpose AI (GPAI) poses risks that, according to leading experts, could lead to the 'marginalisation or extinction of humanity.' To address these risks, there are an increasing number of…
The potential for advances in information-age technologies to undermine nuclear deterrence and influence the potential for nuclear escalation represents a critical question for international politics. One challenge is that uncertainty about…
As frontier artificial intelligence (AI) systems become more capable, it becomes more important that developers can explain why their systems are sufficiently safe. One way to do so is via safety cases: reports that make a structured…
While artificial intelligence (AI) is advancing rapidly and mastering increasingly complex problems with astonishing performance, the safety assurance of such systems is a major concern. Particularly in the context of safety-critical,…
As artificial intelligence (AI) systems are increasingly deployed, principles for ethical AI are also proliferating. Certification offers a method to both incentivize adoption of these principles and substantiate that they have been…
Prominent AI experts have suggested that companies developing high-risk AI systems should be required to show that such systems are safe before they can be developed or deployed. The goal of this paper is to expand on this idea and explore…
Artificial Knowledge (AK) systems are transforming decision-making across critical domains such as healthcare, finance, and criminal justice. However, their growing opacity presents governance challenges that current regulatory approaches,…
Artificial intelligence (AI) advances rapidly but achieving complete human control over AI risks remains an unsolved problem, akin to driving the fast AI "train" without a "brake system." By exploring fundamental control mechanisms at key…
This paper reviews and proposes concerns in adopting, fielding, and maintaining artificial intelligence (AI) systems. While the AI community has made rapid progress, there are challenges in certifying AI systems. Using procedures from…
AI deployment in sensitive domains such as health care, credit, employment, and criminal justice is often treated as unsafe to authorize until model internals can be explained. This often leads to an excessive reliance on mechanistic…
Observers and practitioners of artificial intelligence (AI) have proposed an FDA-style licensing regime for the most advanced AI models, or 'frontier' models. In this paper, we explore the applicability of approval regulation -- that is,…
The adoption of human oversight measures makes it possible to regulate, to varying degrees and in different ways, the decision-making process of Artificial Intelligence (AI) systems, for example by placing a human being in charge of…
The increased adoption of Artificial Intelligence (AI) presents an opportunity to solve many socio-economic and environmental challenges; however, this cannot happen without securing AI-enabled technologies. In recent years, most AI models…
The development of privacy-enhancing technologies has made immense progress in reducing trade-offs between privacy and performance in data exchange and analysis. Similar tools for structured transparency could be useful for AI governance by…
Recent research advances in Artificial Intelligence (AI) have yielded promising results for automated software vulnerability management. AI-based models are reported to greatly outperform traditional static analysis tools, indicating a…
Are nuclear weapons useful for coercion, and, if so, what factors increase the credibility and effectiveness of nuclear threats? While prominent scholars like Thomas Schelling argue that nuclear brinkmanship, or the manipulation of nuclear…