Related papers: Black-box Adversarial Attacks with Limited Queries…

Many optimization methods for generating black-box adversarial examples have been proposed, but the aspect of initializing said optimizers has not been considered in much detail. We show that the choice of starting points is indeed crucial,…

A growing body of work has shown that deep neural networks are susceptible to adversarial examples. These take the form of small perturbations applied to the model's input which lead to incorrect predictions. Unfortunately, most literature…

Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have…

Adversarial perturbations can be added to images to protect their content from unwanted inferences. These perturbations may, however, be ineffective against classifiers that were not {seen} during the generation of the perturbation, or…

We study the problem of attacking a machine learning model in the hard-label black-box setting, where no model information is revealed except that the attacker can make queries to probe the corresponding hard-label decisions. This is a very…

Facially manipulated images and videos or DeepFakes can be used maliciously to fuel misinformation or defame individuals. Therefore, detecting DeepFakes is crucial to increase the credibility of social media platforms and other media…

An adversarial attack paradigm explores various scenarios for the vulnerability of deep learning models: minor changes of the input can force a model failure. Most of the state of the art frameworks focus on adversarial attacks for images…

Recent advancements in diffusion models have enabled high-fidelity and photorealistic image generation across diverse applications. However, these models also present security and privacy risks, including copyright violations, sensitive…

Clustering algorithms play a fundamental role as tools in decision-making and sensible automation processes. Due to the widespread use of these applications, a robustness analysis of this family of algorithms against adversarial noise has…

The evaluation of robustness against adversarial manipulation of neural networks-based classifiers is mainly tested with empirical attacks as methods for the exact computation, even when available, do not scale to large networks. We propose…

Deep learning has made significant breakthroughs in many fields, including electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, deep learning models are vulnerable to adversarial attacks, in which deliberately…

Training robust deep learning models for down-stream tasks is a critical challenge. Research has shown that down-stream models can be easily fooled with adversarial inputs that look like the training data, but slightly perturbed, in a way…

In the past few years, an increasing number of machine-learning and deep learning structures, such as Convolutional Neural Networks (CNNs), have been applied to solving a wide range of real-life problems. However, these architectures are…

Traditional decision-based black-box adversarial attacks on image classifiers aim to generate adversarial examples by slightly modifying input images while keeping the number of queries low, where each query involves sending an input to the…

Many works have investigated the adversarial attacks or defenses under the settings where a bounded and imperceptible perturbation can be added to the input. However in the real-world, the attacker does not need to comply with this…

To launch black-box attacks against a Deep Neural Network (DNN) based Face Recognition (FR) system, one needs to build \textit{substitute} models to simulate the target model, so the adversarial examples discovered from substitute models…

Adversarial attacks on machine learning-based classifiers, along with defense mechanisms, have been widely studied in the context of single-label classification problems. In this paper, we shift the attention to multi-label classification,…

Research in adversarial machine learning has shown how the performance of machine learning models can be seriously compromised by injecting even a small fraction of poisoning points into the training data. While the effects on model…

Applications of machine learning (ML) models and convolutional neural networks (CNNs) have been rapidly increased. Although state-of-the-art CNNs provide high accuracy in many applications, recent investigations show that such networks are…

An intriguing property of deep neural networks is the existence of adversarial examples, which can transfer among different architectures. These transferable adversarial examples may severely hinder deep neural network-based applications.…