AI alignment aims to make AI systems behave in line with human intentions and values. As
AI systems grow more capable, the potential large-scale risks associated with misaligned AI …

Despite the impressive achievements of Deep Neural Networks (DNNs) in computer vision,
their vulnerability to adversarial attacks remains a critical concern. Extensive research has …

The last decade of machine learning has seen drastic increases in scale and capabilities.
Deep neural networks (DNNs) are increasingly being deployed in the real world. However …

External audits of AI systems are increasingly recognized as a key mechanism for AI
governance. The effectiveness of an audit, however, depends on the degree of access …

Interpretable AI tools are often motivated by the goal of understanding model behavior in out-
of-distribution (OOD) contexts. Despite the attention this area of study receives, there are …

This is the interim publication of the first International Scientific Report on the Safety of
Advanced AI. The report synthesises the scientific understanding of general-purpose AI--AI …

Over the past decade, deep learning has revolutionized conventional tasks that rely on hand-
craft feature extraction with its strong feature learning capability, leading to substantial …

Automatically discovering failures in vision models under real-world settings remains an
open challenge. This work demonstrates how off-the-shelf, large-scale, image-to-text and …

Deep Neural Networks (DNNs) have shown impressive performance in computer vision
tasks; however, their vulnerability to adversarial attacks raises concerns regarding their …

While deep learning has led to huge progress in complex image classification tasks like
ImageNet unexpected failure modes eg via spurious features call into question how reliably …