Related papers: NeurIPS Should Require Reproducibility Standards f…
Powerful new frontier AI technologies are bringing many benefits to society but at the same time bring new risks. AI developers and regulators are therefore seeking ways to assure the safety of such systems, and one promising method under…
Frontier AI models -- highly capable foundation models at the cutting edge of AI development -- may pose severe risks to public safety, human rights, economic stability, and societal value in the coming years. These risks could arise from…
AI policymakers are responsible for delivering effective governance mechanisms that can provide safe, aligned and trustworthy AI development. However, the information environment offered to policymakers is characterised by an unnecessarily…
Frontier artificial intelligence (AI) systems pose increasing risks to society, making it essential for developers to provide assurances about their safety. One approach to offering such assurances is through a safety case: a structured,…
As AI systems' sophistication and proliferation have increased, awareness of the risks has grown proportionally (Sorkin et al. 2023). In response, calls have grown for stronger emphasis on disclosure and transparency in the AI industry…
We outline a vision for frontier AI auditing, which we define as rigorous third-party verification of frontier AI developers' safety and security claims, and evaluation of their systems and practices against relevant standards, based on…
Frontier AI developers are increasingly deploying highly capable models internally to automate AI R&D, but these deployments currently face limited external oversight. It is essential, therefore, that developers provide evidence that…
Frontier AI companies first deploy their most advanced models internally, for weeks or months of safety testing, evaluation, and iteration, before a possible public release. For example, Anthropic recently developed a new class of model…
Security evaluations inherently depend on stable identifiers. Any finding, audit, or regulatory decision must remain attached to the specific artifact it pertains to. Continuously updated artificial intelligence systems violate this core…
This position paper argues that behavioural assurance, even when carefully designed, is being asked to carry safety claims it cannot verify. AI governance frameworks enacted between 2019 and early 2026 require reviewable evidence of…
The rapid advancement of AI systems has raised widespread concerns about potential harms of frontier AI systems and the need for responsible evaluation and oversight. In this position paper, we argue that frontier AI companies should report…
The growing societal reliance on artificial intelligence necessitates robust frameworks for ensuring its security, accountability, and trustworthiness. This thesis addresses the complex interplay between privacy, verifiability, and…
Prominent AI companies are producing 'safety frameworks' as a type of voluntary self-governance. These statements purport to establish risk thresholds and safety procedures for the development and deployment of highly capable AI.…
Following the AI Seoul Summit in 2024, twelve AI companies published frontier AI safety frameworks (Frameworks) outlining their approaches to managing catastrophic risks from advanced AI systems. Emerging legislation increasingly treats…
Over the past year, artificial intelligence (AI) companies have been increasingly adopting AI safety frameworks. These frameworks outline how companies intend to keep the potential risks associated with developing and deploying frontier AI…
Advanced AI models hold the promise of tremendous benefits for humanity, but society needs to proactively manage the accompanying risks. In this paper, we focus on what we term "frontier AI" models: highly capable foundation models that…
This paper contributes to the nascent debate around safety cases for frontier AI systems. Safety cases are structured, defensible arguments that a system is acceptably safe to deploy in a given context. Historically, they have been used in…
In the rapidly evolving field of cybersecurity, ensuring the reproducibility of AI-driven research is critical to maintaining the reliability and integrity of security systems. This paper addresses the reproducibility crisis within the…
As Artificial Intelligence (AI) systems proliferate, the need for systematic, transparent, and actionable processes for evaluating them is growing. While many resources exist to support AI evaluation, they have several limitations. Few…
Frontier AI companies increasingly rely on external evaluations to assess risks from dangerous capabilities before deployment. However, external evaluators often receive limited model access, limited information, and little time, which can…