Targeted Nonlinear Adversarial Perturbations in Images and Videos

08/27/2018
by   Roberto Rey-de-Castro, et al.
0

We introduce a method for learning adversarial perturbations targeted to individual images or videos. The learned perturbations are found to be sparse while at the same time containing a high level of feature detail. Thus, the extracted perturbations allow a form of object or action recognition and provide insights into what features the studied deep neural network models consider important when reaching their classification decisions. From an adversarial point of view, the sparse perturbations successfully confused the models into misclassifying, although the perturbed samples still belonged to the same original class by visual examination. This is discussed in terms of a prospective data augmentation scheme. The sparse yet high-quality perturbations may also be leveraged for image or video compression.

READ FULL TEXT
research
03/07/2018

Sparse Adversarial Perturbations for Videos

Although adversarial samples of deep neural networks (DNNs) have been in...
research
12/31/2021

On Distinctive Properties of Universal Perturbations

We identify properties of universal adversarial perturbations (UAPs) tha...
research
07/24/2018

Learning Discriminative Video Representations Using Adversarial Perturbations

Adversarial perturbations are noise-like patterns that can subtly change...
research
06/12/2022

An Efficient Method for Sample Adversarial Perturbations against Nonlinear Support Vector Machines

Adversarial perturbations have drawn great attentions in various machine...
research
09/24/2021

Local Intrinsic Dimensionality Signals Adversarial Perturbations

The vulnerability of machine learning models to adversarial perturbation...
research
07/02/2018

Adversarial Perturbations Against Real-Time Video Classification Systems

Recent research has demonstrated the brittleness of machine learning sys...
research
03/26/2022

Reverse Engineering of Imperceptible Adversarial Image Perturbations

It has been well recognized that neural network based image classifiers ...

Please sign up or login with your details

Forgot password? Click here to reset