Related papers: DARCCC: Detecting Adversaries by Reconstruction fr…
We present a mechanism for detecting adversarial examples based on data representations taken from the hidden layers of the target network. For this purpose, we train individual autoencoders at intermediate layers of the target network.…
Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the training phase of deep neural networks make…
Adversarial reprogramming allows stealing computational resources by repurposing machine learning models to perform a different task chosen by the attacker. For example, a model trained to recognize images of animals can be reprogrammed to…
Deep learning models have been used in creating various effective image classification applications. However, they are vulnerable to adversarial attacks that seek to misguide the models into predicting incorrect classes. Our study of major…
In communication systems, there are many tasks, like modulation recognition, which rely on Deep Neural Networks (DNNs) models. However, these models have been shown to be susceptible to adversarial perturbations, namely imperceptible…
There has been a recent surge in research on adversarial perturbations that defeat Deep Neural Networks (DNNs) in machine vision; most of these perturbation-based attacks target object classifiers. Inspired by the observation that humans…
Reliably detecting anomalies in a given set of images is a task of high practical relevance for visual quality inspection, surveillance, or medical image analysis. Autoencoder neural networks learn to reconstruct normal images, and hence…
In spite of the enormous success of neural networks, adversarial examples remain a relatively weakly understood feature of deep learning systems. There is a considerable effort in both building more powerful adversarial attacks and…
The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges…
Deep neural networks have been shown to be susceptible to adversarial examples -- small, imperceptible changes constructed to cause mis-classification in otherwise highly accurate image classifiers. As a practical alternative, recent work…
Many recent studies have shown that deep neural models are vulnerable to adversarial samples: images with imperceptible perturbations, for example, can fool image classifiers. In this paper, we present the first type-specific approach to…
In the light of recent analyses on privacy-concerning scene revelation from visual descriptors, we develop descriptors that conceal the input image content. In particular, we propose an adversarial learning framework for training visual…
Deep Neural Networks have been shown to be vulnerable to adversarial images. Conventional attacks strive for indistinguishable adversarial images with strictly restricted perturbations. Recently, researchers have moved to explore…
Deep neural network-based image compression has been extensively studied. However, the model robustness which is crucial to practical application is largely overlooked. We propose to examine the robustness of prevailing learned image…
Humans rely heavily on shape information to recognize objects. Conversely, convolutional neural networks (CNNs) are biased more towards texture. This is perhaps the main reason why CNNs are vulnerable to adversarial examples. Here, we…
Deep learning based image recognition systems have been widely deployed on mobile devices in today's world. In recent studies, however, deep learning models are shown vulnerable to adversarial examples. One variant of adversarial examples,…
An adversary can fool deep neural network object detectors by generating adversarial noises. Most of the existing works focus on learning local visible noises in an adversarial "patch" fashion. However, the 2D patch attached to a 3D object…
Since the discovery of adversarial examples - the ability to fool modern CNN classifiers with tiny perturbations of the input, there has been much discussion whether they are a "bug" that is specific to current neural architectures and…
It has been well recognized that neural network based image classifiers are easily fooled by images with tiny perturbations crafted by an adversary. There has been a vast volume of research to generate and defend such adversarial attacks.…
Though Convolutional Neural Networks (CNNs) have surpassed human-level performance on tasks such as object classification and face verification, they can easily be fooled by adversarial attacks. These attacks add a small perturbation to the…