The prosperity of machine learning has been accompanied by increasing attacks on the
training process. Among them, poisoning attacks have become an emerging threat during …

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 …

Large vision-language models (VLMs) such as GPT-4 have achieved unprecedented
performance in response generation, especially with visual inputs, enabling more creative …

Unrestricted adversarial attacks typically manipulate the semantic content of an image (eg,
color or texture) to create adversarial examples that are both effective and photorealistic …

Deep neural networks are vulnerable to adversarial examples that mislead the models with
imperceptible perturbations. Though adversarial attacks have achieved incredible success …

Multimodal Large Language Models (MLLMs) that integrate text and other modalities
(especially vision) have achieved unprecedented performance in various multimodal tasks …

For black-box attacks, the gap between the substitute model and the victim model is usually
large, which manifests as a weak attack performance. Motivated by the observation that the …

Estimating the risk level of adversarial examples is essential for safely deploying machine
learning models in the real world. One popular approach for physical-world attacks is to …

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 …

Transferability of adversarial examples is of central importance for attacking an unknown
model, which facilitates adversarial attacks in more practical scenarios, eg, blackbox attacks …