Related papers: Open-Category Classification by Adversarial Sample…

Adversarial examples are malicious inputs to machine learning models that trigger a misclassification. This type of attack has been studied for close to a decade, and we find that there is a lack of study and formalization of adversary…

We describe a new approach that improves the training of generative adversarial nets (GANs) for synthesizing diverse images from a text input. Our approach is based on the conditional version of GANs and expands on previous work leveraging…

Zero-Shot Learning (ZSL) targets at recognizing unseen categories by leveraging auxiliary information, such as attribute embedding. Despite the encouraging results achieved, prior ZSL approaches focus on improving the discriminant power of…

Adversarial samples are perturbed inputs crafted to mislead the machine learning systems. A training mechanism, called adversarial training, which presents adversarial samples along with clean samples has been introduced to learn robust…

The design of additive imperceptible perturbations to the inputs of deep classifiers to maximize their misclassification rates is a central focus of adversarial machine learning. An alternative approach is to synthesize adversarial examples…

In Generalized Zero-Shot Learning (GZSL), unseen categories (for which no visual data are available at training time) can be predicted by leveraging their class embeddings (e.g., a list of attributes describing them) together with a…

Correctly identifying the type of file under examination is a critical part of a forensic investigation. The file type alone suggests the embedded content, such as a picture, video, manuscript, spreadsheet, etc. In cases where a system…

Learning to classify unseen class samples at test time is popularly referred to as zero-shot learning (ZSL). If test samples can be from training (seen) as well as unseen classes, it is a more challenging problem due to the existence of…

In recent years, image classification, as a core task in computer vision, relies on high-quality labelled data, which restricts the wide application of deep learning models in practical scenarios. To alleviate the problem of insufficient…

The existence of adversarial examples capable of fooling trained neural network classifiers calls for a much better understanding of possible attacks to guide the development of safeguards against them. This includes attack methods in the…

Anomaly detection is a classical problem in computer vision, namely the determination of the normal from the abnormal when datasets are highly biased towards one class (normal) due to the insufficient sample size of the other class…

Adversarial machine learning, i.e., increasing the robustness of machine learning algorithms against so-called adversarial examples, is now an established field. Yet, newly proposed methods are evaluated and compared under unrealistic…

With the progress in AI-based facial forgery (i.e., deepfake), people are increasingly concerned about its abuse. Albeit effort has been made for training classification (also known as deepfake detection) models to recognize such forgeries,…

We propose to generate adversarial samples by modifying activations of upper layers encoding semantically meaningful concepts. The original sample is shifted towards a target sample, yielding an adversarial sample, by using the modified…

In generalized zero shot learning (GZSL), the set of classes are split into seen and unseen classes, where training relies on the semantic features of the seen and unseen classes and the visual representations of only the seen classes,…

Recently, unsupervised adversarial training (AT) has been highlighted as a means of achieving robustness in models without any label information. Previous studies in unsupervised AT have mostly focused on implementing self-supervised…

Generative neural samplers are probabilistic models that implement sampling using feedforward neural networks: they take a random input vector and produce a sample from a probability distribution defined by the network weights. These models…

We extend Generative Adversarial Networks (GANs) to the semi-supervised context by forcing the discriminator network to output class labels. We train a generative model G and a discriminator D on a dataset with inputs belonging to one of N…

Machine learning models, especially neural network (NN) classifiers, have acceptable performance and accuracy that leads to their wide adoption in different aspects of our daily lives. The underlying assumption is that these models are…

While a substantial body of prior work has explored adversarial example generation for natural language understanding tasks, these examples are often unrealistic and diverge from the real-world data distributions. In this work, we introduce…