Deep Learning is the most widely used tool in the contemporary field of computer vision. Its
ability to accurately solve complex problems is employed in vision research to learn deep …

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 …

Adversarial purification refers to a class of defense methods that remove adversarial
perturbations using a generative model. These methods do not make assumptions on the …

As a research community, we are still lacking a systematic understanding of the progress on
adversarial robustness which often makes it hard to identify the most promising ideas in …

Deep learning is at the heart of the current rise of artificial intelligence. In the field of
computer vision, it has become the workhorse for applications ranging from self-driving cars …

A common approach to transfer learning under distribution shift is to fine-tune the last few
layers of a pre-trained model, preserving learned features while also adapting to the new …

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. It is thus
imperative to devise effective attack algorithms to identify the deficiencies of DNNs …

A few years ago, the first CNN surpassed human performance on ImageNet. However, it
soon became clear that machines lack robustness on more challenging test cases, a major …

Fine-tuning pre-trained models has been ubiquitously proven to be effective in a wide range
of NLP tasks. However, fine-tuning the whole model is parameter inefficient as it always …

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 …