相关论文: LocalStyleFool: Regional Video Style Transfer Atta…

This paper investigates the visual quality of the adversarial examples. Recent papers propose to smooth the perturbations to get rid of high frequency artefacts. In this work, smoothing has a different meaning as it perceptually shapes the…

StyleMamba has recently demonstrated efficient text-driven image style transfer by leveraging state-space models (SSMs) and masked directional losses. In this paper, we extend the StyleMamba framework to handle video sequences. We propose…

Recently, deep networks have achieved impressive semantic segmentation performance, in particular thanks to their use of larger contextual information. In this paper, we show that the resulting networks are sensitive not only to global…

The deep neural network is vulnerable to adversarial examples. Adding imperceptible adversarial perturbations to images is enough to make them fail. Most existing research focuses on attacking image classifiers or anchor-based object…

We aim at the problem named One-Shot Unsupervised Domain Adaptation. Unlike traditional Unsupervised Domain Adaptation, it assumes that only one unlabeled target sample can be available when learning to adapt. This setting is realistic but…

Although adversarial samples of deep neural networks (DNNs) have been intensively studied on static images, their extensions in videos are never explored. Compared with images, attacking a video needs to consider not only spatial cues but…

We propose a new adversarial attack to Deep Neural Networks for image classification. Different from most existing attacks that directly perturb input pixels, our attack focuses on perturbing abstract features, more specifically, features…

On-device Vision-Language Models (VLMs) promise data privacy via local execution. However, we show that the architectural shift toward Dynamic High-Resolution preprocessing (e.g., AnyRes) introduces an inherent algorithmic side-channel.…

Transferable adversarial attack has drawn increasing attention due to their practical threaten to real-world applications. In particular, the feature-level adversarial attack is one recent branch that can enhance the transferability via…

This paper presents the first adversarial example based method for attacking human instance segmentation networks, namely person segmentation networks in short, which are harder to fool than classification networks. We propose a novel…

In recent years, there has been increasing interest in applying stylization on 3D scenes from a reference style image, in particular onto neural radiance fields (NeRF). While performing stylization directly on NeRF guarantees appearance…

We propose a novel framework for real-time black-box universal attacks which disrupts activations of early convolutional layers in deep learning models. Our hypothesis is that perturbations produced in the wavelet space disrupt early…

Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly modifying most of its pixels, or by occluding it with a patch. In this paper, we propose a method that keeps…

Visual-Language Pre-training (VLP) models have achieved significant performance across various downstream tasks. However, they remain vulnerable to adversarial examples. While prior efforts focus on improving the adversarial transferability…

Multimodal image fusion and semantic segmentation are critical for autonomous driving. Despite advancements, current models often struggle with segmenting densely packed elements due to a lack of comprehensive fusion features for guidance…

We propose a method to efficiently equip the Segment Anything Model (SAM) with the ability to generate regional captions. SAM presents strong generalizability to segment anything while is short for semantic understanding. By introducing a…

Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been…

Adversarial robustness assessment for video recognition models has raised concerns owing to their wide applications on safety-critical tasks. Compared with images, videos have much high dimension, which brings huge computational costs when…

Currently, style augmentation is capturing attention due to convolutional neural networks (CNN) being strongly biased toward recognizing textures rather than shapes. Most existing styling methods either perform a low-fidelity style transfer…

With video-level labels, weakly supervised temporal action localization (WTAL) applies a localization-by-classification paradigm to detect and classify the action in untrimmed videos. Due to the characteristic of classification,…