Related papers: Universal Defensive Underpainting Patch: Making Yo…
The outstanding capability of diffusion models in generating high-quality images poses significant threats when misused by adversaries. In particular, we assume malicious adversaries exploiting diffusion models for inpainting tasks, such as…
Deep learning image classification is vulnerable to adversarial attack, even if the attacker changes just a small patch of the image. We propose a defense against patch attacks based on partially occluding the image around each candidate…
Blind spots or outright deceit can bedevil and deceive machine learning models. Unidentified objects such as digital "stickers," also known as adversarial patches, can fool facial recognition systems, surveillance systems and self-driving…
Infrared vision-language models (IR-VLMs) have emerged as a promising paradigm for multimodal perception in low-visibility environments, yet their robustness to adversarial attacks remains largely unexplored. Existing adversarial patch…
Patch adversarial attacks on images, in which the attacker can distort pixels within a region of bounded size, are an important threat model since they provide a quantitative model for physical adversarial attacks. In this paper, we…
Wide deployment of deep neural networks (DNNs) based applications (e.g., style transfer, cartoonish), stimulating the requirement of copyright protection of such application's production. Although some traditional visible copyright…
Digital versions of real-world text documents often suffer from issues like environmental corrosion of the original document, low-quality scanning, or human interference. Existing document restoration and inpainting methods typically…
Invisible watermarks safeguard images' copyrights by embedding hidden messages only detectable by owners. They also prevent people from misusing images, especially those generated by AI models. We propose a family of regeneration attacks to…
We present an end-to-end trainable approach for Optical Character Recognition (OCR) on printed documents. Specifically, we propose a model that predicts a) a two-dimensional character grid (\emph{chargrid}) representation of a document…
Privacy protection is an important research area, which is especially critical in this big data era. To a large extent, the privacy of visual classification data is mainly in the mapping between the image and its corresponding label, since…
Object detection forms a key component in Unmanned Aerial Vehicles (UAVs) for completing high-level tasks that depend on the awareness of objects on the ground from an aerial perspective. In that scenario, adversarial patch attacks on an…
CAPTCHA (Completely Automated Public Truing test to tell Computers and Humans Apart) is a widely used technology to distinguish real users and automated users such as bots. However, the advance of AI technologies weakens many CAPTCHA tests…
Ancient history relies on the study of ancient characters. However, real-world scanned oracle characters are difficult to collect and annotate, posing a major obstacle for oracle character recognition (OrCR). Besides, serious abrasion and…
In Document Understanding, the challenge of reconstructing damaged, occluded, or incomplete text remains a critical yet unexplored problem. Subsequent document understanding tasks can benefit from a document reconstruction process. In…
Face anti-spoofing is essential to prevent false facial verification by using a photo, video, mask, or a different substitute for an authorized person's face. Most of the state-of-the-art presentation attack detection (PAD) systems suffer…
Recent development of Under-Display Camera (UDC) systems provides a true bezel-less and notch-free viewing experience on smartphones (and TV, laptops, tablets), while allowing images to be captured from the selfie camera embedded…
Recently, deep neural networks (DNNs) have been widely and successfully used in Object Detection, e.g. Faster RCNN, YOLO, CenterNet. However, recent studies have shown that DNNs are vulnerable to adversarial attacks. Adversarial attacks…
In the ever-evolving adversarial machine learning landscape, developing effective defenses against patch attacks has become a critical challenge, necessitating reliable solutions to safeguard real-world AI systems. Although diffusion models…
Image outpainting seeks for a semantically consistent extension of the input image beyond its available content. Compared to inpainting -- filling in missing pixels in a way coherent with the neighboring pixels -- outpainting can be…
Digital watermarking enables protection against copyright infringement of images. Although existing methods embed watermarks imperceptibly and demonstrate robustness against attacks, they typically lack resilience against geometric…