Related papers: Semi-Adversarial Networks: Convolutional Autoencod…

This is Btech thesis report on detection and purification of adverserially attacked images. A deep learning model is trained on certain training examples for various tasks such as classification, regression etc. By training, weights are…

Deep neural networks are known to be vulnerable to adversarial examples, i.e., images that are maliciously perturbed to fool the model. Generating adversarial examples has been mostly limited to finding small perturbations that maximize the…

Machine Learning models are vulnerable to adversarial attacks that rely on perturbing the input data. This work proposes a novel strategy using Autoencoder Deep Neural Networks to defend a machine learning model against two gradient-based…

While adversarial neural networks have been shown successful for static image attacks, very few approaches have been developed for attacking online image streams while taking into account the underlying physical dynamics of autonomous…

Numerous recent studies have demonstrated how Deep Neural Network (DNN) classifiers can be fooled by adversarial examples, in which an attacker adds perturbations to an original sample, causing the classifier to misclassify the sample.…

Transfer learning has emerged as a powerful methodology for adapting pre-trained deep neural networks on image recognition tasks to new domains. This process consists of taking a neural network pre-trained on a large feature-rich source…

In many real-world applications, face recognition models often degenerate when training data (referred to as source domain) are different from testing data (referred to as target domain). To alleviate this mismatch caused by some factors…

Current works formulate facial action unit (AU) recognition as a supervised learning problem, requiring fully AU-labeled facial images during training. It is challenging if not impossible to provide AU annotations for large numbers of…

With the broad use of face recognition, its weakness gradually emerges that it is able to be attacked. So, it is important to study how face recognition networks are subject to attacks. In this paper, we focus on a novel way to do attacks…

Autoencoder can give rise to an appropriate latent representation of the input data, however, the representation which is solely based on the intrinsic property of the input data, is usually inferior to express some semantic information. A…

Machine learning models can learn from data samples to carry out various tasks efficiently. When data samples are adversarially manipulated, such as by insertion of carefully crafted noise, it can cause the model to make mistakes. Quantum…

Recent developments in biosignal processing have enabled users to exploit their physiological status for manipulating devices in a reliable and safe manner. One major challenge of physiological sensing lies in the variability of biosignals…

The rapid growth of social media has led to the widespread sharing of individual portrait images, which pose serious privacy risks due to the capabilities of automatic face recognition (AFR) systems for mass surveillance. Hence, protecting…

Recently, generative adversarial networks and adversarial autoencoders have gained a lot of attention in machine learning community due to their exceptional performance in tasks such as digit classification and face recognition. They map…

In recent years, machine learning algorithms have been applied widely in various fields such as health, transportation, and the autonomous car. With the rapid developments of deep learning techniques, it is critical to take the security…

Social network alignment aims at aligning person identities across social networks. Embedding based models have been shown effective for the alignment where the structural proximity preserving objective is typically adopted for the model…

Image generating neural networks are mostly viewed as black boxes, where any change in the input can have a number of globally effective changes on the output. In this work, we propose a method for learning disentangled representations to…

Inspired by the effectiveness of adversarial training in the area of Generative Adversarial Networks we present a new approach for learning feature representations in person re-identification. We investigate different types of bias that…

This paper presents a novel, fast and privacy preserving implementation of deep autoencoders. DAEF (Deep Autoencoder for Federated learning), unlike traditional neural networks, trains a deep autoencoder network in a non-iterative way,…

We consider the problem of face swapping in images, where an input identity is transformed into a target identity while preserving pose, facial expression, and lighting. To perform this mapping, we use convolutional neural networks trained…