Related papers: Generating Out of Distribution Adversarial Attack …
The deep neural network is vulnerable to adversarial examples. Adding imperceptible adversarial perturbations to images is enough to make them fail. Most existing research focuses on attacking image classifiers or anchor-based object…
In recent years, Generative Adversarial Networks (GANs) have shown substantial progress in modeling complex distributions of data. These networks have received tremendous attention since they can generate implicit probabilistic models that…
Modern image classification systems are often built on deep neural networks, which suffer from adversarial examples--images with deliberately crafted, imperceptible noise to mislead the network's classification. To defend against…
Adversarial examples (AEs) are images that can mislead deep neural network (DNN) classifiers via introducing slight perturbations into original images. This security vulnerability has led to vast research in recent years because it can…
With the rise in popularity of machine and deep learning models, there is an increased focus on their vulnerability to malicious inputs. These adversarial examples drift model predictions away from the original intent of the network and are…
Inspired by biophysical principles underlying nonlinear dendritic computation in neural circuits, we develop a scheme to train deep neural networks to make them robust to adversarial attacks. Our scheme generates highly nonlinear, saturated…
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…
The GANs are generative models whose random samples realistically reflect natural images. It also can generate samples with specific attributes by concatenating a condition vector into the input, yet research on this field is not well…
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…
Machine learning has become an important component for many systems and applications including computer vision, spam filtering, malware and network intrusion detection, among others. Despite the capabilities of machine learning algorithms…
A number of online services nowadays rely upon machine learning to extract valuable information from data collected in the wild. This exposes learning algorithms to the threat of data poisoning, i.e., a coordinate attack in which a fraction…
We propose a novel approach for generating unrestricted adversarial examples by manipulating fine-grained aspects of image generation. Unlike existing unrestricted attacks that typically hand-craft geometric transformations, we learn…
Several machine learning models, including neural networks, consistently misclassify adversarial examples---inputs formed by applying small but intentionally worst-case perturbations to examples from the dataset, such that the perturbed…
Though generative adversarial networks (GANs) areprominent models to generate realistic and crisp images,they often encounter the mode collapse problems and arehard to train, which comes from approximating the intrinsicdiscontinuous…
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.…
Malware detectors based on machine learning (ML) have been shown to be susceptible to adversarial malware examples. However, current methods to generate adversarial malware examples still have their limits. They either rely on detailed…
Sequence-based deep learning models (e.g., RNNs), can detect malware by analyzing its behavioral sequences. Meanwhile, these models are susceptible to adversarial attacks. Attackers can create adversarial samples that alter the sequence…
Recent studies have shown that modern deep neural network classifiers are easy to fool, assuming that an adversary is able to slightly modify their inputs. Many papers have proposed adversarial attacks, defenses and methods to measure…
Deep neural networks suffer from over-fitting and catastrophic forgetting when trained with small data. One natural remedy for this problem is data augmentation, which has been recently shown to be effective. However, previous works either…
State-of-the-art generative model-based attacks against image classifiers overwhelmingly focus on single-object (i.e., single dominant object) images. Different from such settings, we tackle a more practical problem of generating…