Diffusion models have emerged as a powerful new family of deep generative models with
record-breaking performance in many applications, including image synthesis, video …

Despite efforts to align large language models (LLMs) with human values, widely-used
LLMs such as GPT, Llama, Claude, and PaLM are susceptible to jailbreaking attacks …

Masked autoencoders (MAE) is a deep learning method based on Transformer. Originally
used for images, it has now been extended to video, audio, and some other temporal …

Backdoor inversion, the process of finding a backdoor trigger inserted into a machine
learning model, has become the pillar of many backdoor detection and defense methods …

While prior research has proposed a plethora of methods that build neural classifiers robust
against adversarial robustness, practitioners are still reluctant to adopt them due to their …

Adversarial examples that can fool neural network classifiers have attracted much attention.
Existing approaches to detect adversarial examples leverage a supervised scheme in …

Diffusion models have become popular in computer vision applications due to their ability to
generate high-quality images quickly, with some models achieving a high degree of realism …

A certifiably robust classifier implies the one that is theoretically guaranteed to provide
robust predictions against any adversarial attacks under certain conditions. Recent defense …

Adversarial attacks can mislead neural network classifiers. The defense against adversarial
attacks is important for AI safety. Adversarial purification is a family of approaches that …

Malware, or software designed with harmful intent, is an ever-evolving threat that can have
drastic effects on both individuals and institutions. Neural network malware classification …