Add to ORKGMachine learning models exhibit vulnerability to adversarial examples i.e., artificially created inputs that become misinterpreted. The goal of this work is to explore black-box adversarial attacks on deep networks performing image classification. The role of surrogate machine learning models for adversarial attacks is studied, and a special version of a genetic algorithm for generating adversarial examples is proposed. The efficiency of attacks is validated by a multitude of experiments with the Fashion MNIST data set. The experimental results verify the usability of our approach with surprisingly good performance in several cases, such as non-targeted attack on residual networks
Computer vision algorithms, such as those implementing object detection, are known to be susceptible...
As modern technology is rapidly progressing, more applications are utilizing aspects of machine lear...
Despite the impressive performances reported by deep neural networks in different application domain...
Adversarial examples are inputs to a machine learning system intentionally crafted by an attacker to...
Deep neural networks have been recently achieving high accuracy on many important tasks, most notabl...
In recent years, adversarial attack methods have been deceived rather easily on deep neural networks...
Deep Neural Networks (DNNs) have demonstrated remarkable performance in a diverse range of applicati...
Deep neural network approaches have made remarkable progress in many machine learning tasks. However...
International audienceRecent studies have demonstrated that the deep neural networks (DNNs) are vuln...
Maliciously manipulated inputs for attacking machine learning methods – in particular deep neural ne...
Deep neural networks (DNNs) have rapidly advanced the state of the art in many important, difficult ...
Machine learning systems based on deep neural networks, being able to produce state-of-the-art resul...
With the rapidly increasing popularity of deep neural networks for image recognition tasks, a parall...
In the thesis, we explore the prospects of creating adversarial examples using various generative mo...
Deep neural networks (DNNs) provide excellent performance in image recognition, speech recognition, ...
Computer vision algorithms, such as those implementing object detection, are known to be susceptible...
As modern technology is rapidly progressing, more applications are utilizing aspects of machine lear...
Despite the impressive performances reported by deep neural networks in different application domain...
Adversarial examples are inputs to a machine learning system intentionally crafted by an attacker to...
Deep neural networks have been recently achieving high accuracy on many important tasks, most notabl...
In recent years, adversarial attack methods have been deceived rather easily on deep neural networks...
Deep Neural Networks (DNNs) have demonstrated remarkable performance in a diverse range of applicati...
Deep neural network approaches have made remarkable progress in many machine learning tasks. However...
International audienceRecent studies have demonstrated that the deep neural networks (DNNs) are vuln...
Maliciously manipulated inputs for attacking machine learning methods – in particular deep neural ne...
Deep neural networks (DNNs) have rapidly advanced the state of the art in many important, difficult ...
Machine learning systems based on deep neural networks, being able to produce state-of-the-art resul...
With the rapidly increasing popularity of deep neural networks for image recognition tasks, a parall...
In the thesis, we explore the prospects of creating adversarial examples using various generative mo...
Deep neural networks (DNNs) provide excellent performance in image recognition, speech recognition, ...
Computer vision algorithms, such as those implementing object detection, are known to be susceptible...
As modern technology is rapidly progressing, more applications are utilizing aspects of machine lear...
Despite the impressive performances reported by deep neural networks in different application domain...