Related papers: Amnesia as a Catalyst for Enhancing Black Box Pixe…
Vision transformers (ViTs) have demonstrated impressive performance and stronger adversarial robustness compared to Convolutional Neural Networks (CNNs). On the one hand, ViTs' focus on global interaction between individual patches reduces…
The vulnerability of the high-performance machine learning models implies a security risk in applications with real-world consequences. Research on adversarial attacks is beneficial in guiding the development of machine learning models on…
The output of Deep Neural Networks (DNN) can be altered by a small perturbation of the input in a black box setting by making multiple calls to the DNN. However, the high computation and time required makes the existing approaches unusable.…
Adversarial perturbations are a useful way to expose vulnerabilities in object detectors. Existing perturbation methods are frequently white-box, architecture specific and use a loss function. More importantly, while they are often…
Recent works have shown that deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify. Even with access only to the model's output, an attacker can employ…
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…
Deep neural networks are facing severe threats from adversarial attacks. Most existing black-box attacks fool target model by generating either global perturbations or local patches. However, both global perturbations and local patches…
Adversarial machine learning is an emerging area showing the vulnerability of deep learning models. Exploring attack methods to challenge state of the art artificial intelligence (A.I.) models is an area of critical concern. The reliability…
Deep learning techniques have shown promising results in image compression, with competitive bitrate and image reconstruction quality from compressed latent. However, while image compression has progressed towards a higher peak…
Most existing works of adversarial samples focus on attacking image recognition models, while little attention is paid to the image retrieval task. In this paper, we identify two inherent challenges in applying prevailing image recognition…
Although deep neural networks have been very successful in image-classification tasks, they are prone to adversarial attacks. To generate adversarial inputs, there has emerged a wide variety of techniques, such as black- and whitebox…
Deep neural networks have recently achieved tremendous success in image classification. Recent studies have however shown that they are easily misled into incorrect classification decisions by adversarial examples. Adversaries can even…
Recent advances in deep learning research have shown remarkable achievements across many tasks in computer vision (CV) and natural language processing (NLP). At the intersection of CV and NLP is the problem of image captioning, where the…
Current deep learning architectures suffer from catastrophic forgetting, a failure to retain knowledge of previously learned classes when incrementally trained on new classes. The fundamental roadblock faced by deep learning methods is that…
Machine unlearning aims to remove specific concepts from pretrained text-to-image diffusion models, yet several white- and black-box attacks have been introduced to make the model generate such unlearned concepts. These attacks,…
No-Reference Image Quality Assessment (NR-IQA) aims to predict image quality scores consistent with human perception without relying on pristine reference images, serving as a crucial component in various visual tasks. Ensuring the…
Machine learning models have been shown vulnerable to adversarial attacks launched by adversarial examples which are carefully crafted by attacker to defeat classifiers. Deep learning models cannot escape the attack either. Most of…
Researchers have repeatedly shown that it is possible to craft adversarial attacks on deep classifiers (small perturbations that significantly change the class label), even in the "black-box" setting where one only has query access to the…
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Many adversarial attacks belong to the category of dense attacks, which…
Deep learning models are vulnerable to external attacks. In this paper, we propose a Reinforcement Learning (RL) based approach to generate adversarial examples for the pre-trained (target) models. We assume a semi black-box setting where…