Related papers: Model evaluation for extreme risks
Large Language Models (LLMs) exhibit surprisingly diverse risk preferences when acting as AI decision makers, a crucial characteristic whose origins remain poorly understood despite their expanding economic roles. We analyze 50 LLMs using…
Machine learning models are usually evaluated according to the average case performance on the test set. However, this is not always ideal, because in some sensitive domains (e.g. autonomous driving), it is the worst case performance that…
Integrating Artificial Intelligence (AI) into mobile and wearables offers numerous benefits at individual, societal, and environmental levels. Yet, it also spotlights concerns over emerging risks. Traditional assessments of risks and…
Large language models (LLMs) have become increasingly sophisticated, leading to widespread deployment in sensitive applications where safety and reliability are paramount. However, LLMs have inherent risks accompanying them, including bias,…
The evaluation of supervised machine learning models is a critical stage in the development of reliable predictive systems. Despite the widespread availability of machine learning libraries and automated workflows, model assessment is often…
Recent advances in AI are transforming AI's ubiquitous presence in our world from that of standalone AI-applications into deeply integrated AI-agents. These changes have been driven by agents' increasing capability to autonomously make…
Digital technologies are constantly changing, and with it criminals are finding new ways to abuse these technologies. Cybercrime investigators, then, must also keep their skills and knowledge up to date. This work proposes a holistic…
Artificial Intelligence (AI) has made impressive progress in recent years and represents a key technology that has a crucial impact on the economy and society. However, it is clear that AI and business models based on it can only reach…
As AI systems become more advanced, companies and regulators will make difficult decisions about whether it is safe to train and deploy them. To prepare for these decisions, we investigate how developers could make a 'safety case,' which is…
Additional training of a deep learning model can cause negative effects on the results, turning an initially positive sample into a negative one (degradation). Such degradation is possible in real-world use cases due to the diversity of…
Rapid development of advanced modelling techniques gives an opportunity to develop tools that are more and more accurate. However as usually, everything comes with a price and in this case, the price to pay is to loose interpretability of a…
Safety cases for frontier AI systems should provide a convincing argument, supported by evidence, that the risk of harm is within an acceptable bound. When developers author their own safety cases, confirmation bias and conflicted…
This paper is intended to provide an overview of how the evaluation of standards could be applied to entity resolution, or record linkage. Data quality is of critical importance for many AI applications, and the quality of data,…
Estimation of extreme conditional quantiles is often required for risk assessment of natural hazards in climate and geo-environmental sciences and for quantitative risk management in statistical finance, econometrics, and actuarial…
This paper proposes a comprehensive analysis of existing concepts coming from different disciplines tackling the notion of intelligence, namely psychology and engineering, and from disciplines aiming to regulate AI innovations, namely AI…
Large AI Models (LAIMs), of which large language models are the most prominent recent example, showcase some impressive performance. However they have been empirically found to pose serious security issues. This paper systematizes our…
Recent progress in artificial intelligence (AI) has drawn attention to the technology's transformative potential, including what some see as its prospects for causing large-scale harm. We review two influential arguments purporting to show…
Effective collaboration between humans and AI-based systems requires effective modeling of the human in the loop, both in terms of the mental state as well as the physical capabilities of the latter. However, these models can also open up…
We present a dependency model tailored to the context of current challenges in data strategies and make recommendations for the cybersecurity community. The model can be used for cyber risk estimation and assessment and generic risk impact…
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…