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 …

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 …

Following the success in advancing natural language processing and understanding,
transformers are expected to bring revolutionary changes to computer vision. This work …

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 …

Deep learning has presented remarkable progress in various tasks. Despite the excellent
performance, deep learning models remain not robust, especially to well-designed …

Certified patch defenses can guarantee robustness of an image classifier to arbitrary
changes within a bounded contiguous region. But, currently, this robustness comes at a cost …

With the rapid advancement of multimodal learning, pre-trained Vision-Language Models
(VLMs) such as CLIP have demonstrated remarkable capacities in bridging the gap between …

The query-based black-box attacks have raised serious threats to machine learning models
in many real applications. In this work, we study a lightweight defense method, dubbed …

Real-world data is complex and often consists of objects that can be decomposed into
multiple entities (eg images into pixels, graphs into interconnected nodes). Randomized …

We present a new certification method for image and point cloud segmentation based on
randomized smoothing. The method leverages a novel scalable algorithm for prediction and …