相关论文: Pre-Deployment Information Sharing: A Zoning Taxon…
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…
Mitigating the risks from frontier AI systems requires up-to-date and reliable information about those systems. Organizations that develop and deploy frontier systems have significant access to such information. By reporting safety-critical…
As Artificial Intelligence (AI) systems increasingly underpin critical applications, from autonomous vehicles to biometric authentication, their vulnerability to transferable attacks presents a growing concern. These attacks, designed to…
A concern about cutting-edge or "frontier" AI foundation models is that an adversary may use the models for preparing chemical, biological, radiological, nuclear, (CBRN), cyber, or other attacks. At least two methods can identify foundation…
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…
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…
Prior access to domain knowledge could significantly improve the performance of a reinforcement learning agent. In particular, it could help agents avoid potentially catastrophic exploratory actions, which would otherwise have to be…
We present a quantitative model for tracking dangerous AI capabilities over time. Our goal is to help the policy and research community visualise how dangerous capability testing can give us an early warning about approaching AI risks. We…
Given rapid progress toward advanced AI and risks from frontier AI systems (advanced AI systems pushing the boundaries of the AI capabilities frontier), the creation and implementation of AI governance and regulatory schemes deserves…
Any human-designed system can potentially be exploited in ways that its designers did not envision, and information systems or networks using quantum components do not escape this reality. We are presented with a unique but quickly waning…
Artificial intelligence (AI) systems will increasingly be used to cause harm as they grow more capable. In fact, AI systems are already starting to be used to automate fraudulent activities, violate human rights, create harmful fake images,…
The most advanced future AI systems will first be deployed inside the frontier AI companies developing them. According to these companies and independent experts, AI systems may reach or even surpass human intelligence and capabilities by…
Cyber threat intelligence is the provision of evidence-based knowledge about existing or emerging threats. Benefits from threat intelligence include increased situational awareness, efficiency in security operations, and improved…
IT security community is recently facing a change of trend from closed to open working groups and from restrictive information to full information disclosure and sharing. One major feature for this trend change is the number of incidents…
Disease maps display the spatial pattern in disease risk, so that high-risk clusters can be identified. The spatial structure in the risk map is typically represented by a set of random effects, which are modelled with a conditional…
The governance of frontier general-purpose artificial intelligence has become a public-sector problem of institutional design, not merely a technical issue of model performance. Recent evidence indicates that AI capabilities are advancing…
Organizations and governments that develop, deploy, use, and govern AI must coordinate on effective risk mitigation. However, the landscape of AI risk mitigation frameworks is fragmented, uses inconsistent terminology, and has gaps in…
Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavior could be very hard to detect, and if present in future…
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…
The increasing cyber threats to critical infrastructure highlight the importance of private companies and government agencies in detecting and sharing information about threat activities. Although the need for improved threat information…