Related papers: AI Failures: A Review of Underlying Issues

AI services are known to have unstable behavior when subjected to changes in data, models or users. Such behaviors, whether triggered by omission or commission, lead to trust issues when AI works with humans. The current approach of…

As frontier AI systems advance toward transformative capabilities, we need a parallel transformation in how we measure and evaluate these systems to ensure safety and inform governance. While benchmarks have been the primary method for…

As AI systems become more capable, integrated, and widespread, understanding the associated risks becomes increasingly important. This paper maps the full spectrum of AI risks, from current harms affecting individual users to existential…

Collaborative AI systems (CAISs) aim at working together with humans in a shared space to achieve a common goal. This critical setting yields hazardous circumstances that could harm human beings. Thus, building such systems with strong…

Artificial intelligence (AI) is being ubiquitously adopted to automate processes in science and industry. However, due to its often intricate and opaque nature, AI has been shown to possess inherent vulnerabilities which can be maliciously…

International agreements about AI development may be required to reduce catastrophic risks from advanced AI systems. However, agreements about such a high-stakes technology must be backed by verification mechanisms--processes or tools that…

Artificial Intelligence (AI) systems exert a growing influence on our society. As they become more ubiquitous, their potential negative impacts also become evident through various real-world incidents. Following such early incidents,…

As modern video games become increasingly complex, traditional manual testing methods are proving costly and inefficient, limiting the ability to ensure high-quality game experiences. While advancements in Artificial Intelligence (AI) offer…

Artificial Intelligence (AI) systems are increasingly used in high-stakes domains of our life, increasing the need to explain these decisions and to make sure that they are aligned with how we want the decision to be made. The field of…

The exposure of security vulnerabilities in safety-aligned language models, e.g., susceptibility to adversarial attacks, has shed light on the intricate interplay between AI safety and AI security. Although the two disciplines now come…

This paper examines the intricate interplay among AI safety, security, and governance by integrating technical systems engineering with principles of moral imagination and ethical philosophy. Drawing on foundational insights from Weapons of…

Current advances in research, development and application of artificial intelligence (AI) systems have yielded a far-reaching discourse on AI ethics. In consequence, a number of ethics guidelines have been released in recent years. These…

This paper summarizes and evaluates various approaches, methods, and techniques for pursuing fairness in artificial intelligence (AI) systems. It examines the merits and shortcomings of these measures and proposes practical guidelines for…

Every AI system is deployed by a human organization. In high risk applications, the combined human plus AI system must function as a high-reliability organization in order to avoid catastrophic errors. This short note reviews the properties…

While much research in artificial intelligence (AI) has focused on scaling capabilities, the accelerating pace of development makes countervailing work on producing harmless, "aligned" systems increasingly urgent. Yet research on alignment…

When AI agents don't align their actions with human values they may cause serious harm. One way to solve the value alignment problem is by including a human operator who monitors all of the agent's actions. Despite the fact, that this…

Building reliable deception detectors for AI systems -- methods that could predict when an AI system is being strategically deceptive without necessarily requiring behavioural evidence -- would be valuable in mitigating risks from advanced…

While the operationalisation of high-level AI ethics principles into practical AI/ML systems has made progress, there is still a theory-practice gap in managing tensions between the underlying AI ethics aspects. We cover five approaches for…

The potential presented by Artificial Intelligence (AI) for healthcare has long been recognised by the technical community. More recently, this potential has been recognised by policymakers, resulting in considerable public and private…

As Artificial Intelligence (AI) becomes increasingly embedded in financial decision-making, the opacity of complex models presents significant challenges for professionals and regulators. While the field of Explainable AI (XAI) attempts to…