Related papers: Beyond Free Riding: Quality of Indicators for Asse…
To ensure that social networks (e.g. opinion consensus, cooperative estimation, distributed learning and adaptation etc.) proliferate and efficiently operate, the participating agents need to collaborate with each other by repeatedly…
Exposure characterization in regional risk assessment aims to assign physical properties to the assets of interest so they can be associated with damage and loss functions. While this process has benefited from the growing availability of…
Cyber threat intelligence (CTI) is essential for effective system defense. CTI is a collection of information about current or past threats to a computer system. This information is gathered by an agent through observation, or based on a…
Federated learning algorithms are developed both for efficiency reasons and to ensure the privacy and confidentiality of personal and business data, respectively. Despite no data being shared explicitly, recent studies showed that the…
Over the past decade, an ecosystem of measures has emerged to evaluate the social and ethical implications of AI systems, largely shaped by high-level ethics principles. These measures are developed and used in fragmented ways, without…
Following the rapid increase in Artificial Intelligence (AI) capabilities in recent years, the AI community has voiced concerns regarding possible safety risks. To support decision-making on the safe use and development of AI systems, there…
Recent work~\cite{Liu2016} has shown that dependencies between items in a dataset can lead to privacy leaks. We extend this concept to privacy-preserving transformations, considering a broader set of dependencies captured by correlation…
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…
High-impact and potentially dangerous capabilities can and should be broken down into early warning shots long before reaching red lines. Each of these early warning shots should correspond to a precursory capability. Each precursory…
We investigate the Free Energy Principle as a foundation for measuring risk in agentic and multi-agent systems. From these principles we introduce a Cumulative Risk Exposure metric that is flexible to differing contexts and needs. We…
We introduce the QIC-Index, a novel metric to address the failure of publication-centric metrics to value research data sharing. The QIC-Index quantifies the impact of individual data objects by calculating a score based on their Quality…
Reducing the spread of misinformation is challenging. AI-based fact verification systems offer a promising solution by addressing the high costs and slow pace of traditional fact-checking. However, the problem of how to effectively…
Advanced AI systems offer substantial benefits but also introduce risks. In 2025, AI-enabled cyber offense has emerged as a concrete example. This technical report applies a quantitative risk modeling methodology (described in full in a…
Data sharing is the fuel of the galloping artificial intelligence economy, providing diverse datasets for training robust models. Trust between data providers and data consumers is widely considered one of the most important factors for…
Responsible AI (RAI) content work, such as annotation, moderation, or red teaming for AI safety, often exposes crowd workers to potentially harmful content. While prior work has underscored the importance of communicating well-being risk to…
Effective coordination of agents actions in partially-observable domains is a major challenge of multi-agent systems research. To address this, many researchers have developed techniques that allow the agents to make decisions based on…
Artificial Intelligence (AI) systems have historically been used as tools that execute narrowly defined tasks. Yet recent advances in AI have unlocked possibilities for a new class of models that genuinely collaborate with humans in complex…
There is an increasing need to share threat information for the prevention of widespread cyber-attacks. While threat-related information sharing can be conducted through traditional information exchange methods, such as email communications…
In this paper we study the problem of information sharing among rational self-interested agents as a dynamic game of asymmetric information. We assume that the agents imperfectly observe a Markov chain and they are called to decide whether…
The emergence of the Internet of Things (IoT) technology has caused a powerful transition in the cyber threat landscape. As a result, organisations have had to find new ways to better manage the risks associated with their infrastructure.…