Related papers: Parallel Rectangle Flip Attack: A Query-based Blac…
Blackbox adversarial attacks can be categorized into transfer- and query-based attacks. Transfer methods do not require any feedback from the victim model, but provide lower success rates compared to query-based methods. Query attacks often…
Deep Neural Networks can be easily fooled by small and imperceptible perturbations. The query-based black-box attack (QBBA) is able to create the perturbations using model output probabilities of image queries requiring no access to the…
Much effort has been made to explain and improve the success of transfer-based attacks (TBA) on black-box computer vision models. This work provides the first attempt at a priori prediction of attack success by identifying the presence of…
Adversarial example detection is known to be an effective adversarial defense method. Black-box attack, which is a more realistic threat and has led to various black-box adversarial training-based defense methods, however, does not attract…
With the growing deployment of sequential recommender systems in e-commerce and other fields, their black-box interfaces raise security concerns: models are vulnerable to extraction and subsequent adversarial manipulation. Existing…
Deep neural networks are powerful and popular learning models that achieve state-of-the-art pattern recognition performance on many computer vision, speech, and language processing tasks. However, these networks have also been shown…
Deep neural network models are massively deployed on a wide variety of hardware platforms. This results in the appearance of new attack vectors that significantly extend the standard attack surface, extensively studied by the adversarial…
Deep models have shown their vulnerability when processing adversarial samples. As for the black-box attack, without access to the architecture and weights of the attacked model, training a substitute model for adversarial attacks has…
Recently, detecting AI-generated images produced by diffusion-based models has attracted increasing attention due to their potential threat to safety. Among existing approaches, reconstruction-based methods have emerged as a prominent…
Enhancing our understanding of adversarial examples is crucial for the secure application of machine learning models in real-world scenarios. A prevalent method for analyzing adversarial examples is through a frequency-based approach.…
This study provides a new understanding of the adversarial attack problem by examining the correlation between adversarial attack and visual attention change. In particular, we observed that: (1) images with incomplete attention regions are…
Adversarial attacks have long been developed for revealing the vulnerability of Deep Neural Networks (DNNs) by adding imperceptible perturbations to the input. Most methods generate perturbations like normal noise, which is not…
A distribution inference attack aims to infer statistical properties of data used to train machine learning models. These attacks are sometimes surprisingly potent, but the factors that impact distribution inference risk are not well…
This paper proposes the Parallel Residual Bi-Fusion Feature Pyramid Network (PRB-FPN) for fast and accurate single-shot object detection. Feature Pyramid (FP) is widely used in recent visual detection, however the top-down pathway of FP…
Deep neural networks (DNNs) have been showed to be highly vulnerable to imperceptible adversarial perturbations. As a complementary type of adversary, patch attacks that introduce perceptible perturbations to the images have attracted the…
Recently, the field of adversarial machine learning has been garnering attention by showing that state-of-the-art deep neural networks are vulnerable to adversarial examples, stemming from small perturbations being added to the input image.…
Due to the advances in deep learning, visually-aware recommender systems (RS) have recently attracted increased research interest. Such systems combine collaborative signals with images, usually represented as feature vectors outputted by…
The prosperous development of Artificial Intelligence-Generated Content (AIGC) has brought people's anxiety about the spread of false information on social media. Designing detectors for filtering is an effective defense method, but most…
Neural text ranking models have witnessed significant advancement and are increasingly being deployed in practice. Unfortunately, they also inherit adversarial vulnerabilities of general neural models, which have been detected but remain…
Powerful adversarial attack methods are vital for understanding how to construct robust deep neural networks (DNNs) and for thoroughly testing defense techniques. In this paper, we propose a black-box adversarial attack algorithm that can…