DeepAI AI Chat
Log In Sign Up

Just Noticeable Difference for Machine Perception and Generation of Regularized Adversarial Images with Minimal Perturbation

02/16/2021
by   Adil Kaan Akan, et al.
0

In this study, we introduce a measure for machine perception, inspired by the concept of Just Noticeable Difference (JND) of human perception. Based on this measure, we suggest an adversarial image generation algorithm, which iteratively distorts an image by an additive noise until the machine learning model detects the change in the image by outputting a false label. The amount of noise added to the original image is defined as the gradient of the cost function of the machine learning model. This cost function explicitly minimizes the amount of perturbation applied on the input image and it is regularized by bounded range and total variation functions to assure perceptual similarity of the adversarial image to the input. We evaluate the adversarial images generated by our algorithm both qualitatively and quantitatively on CIFAR10, ImageNet, and MS COCO datasets. Our experiments on image classification and object detection tasks show that adversarial images generated by our method are both more successful in deceiving the recognition/detection model and less perturbed compared to the images generated by the state-of-the-art methods.

READ FULL TEXT

page 6

page 7

page 9

01/29/2020

Just Noticeable Difference for Machines to Generate Adversarial Images

One way of designing a robust machine learning algorithm is to generate ...
06/17/2022

Minimum Noticeable Difference based Adversarial Privacy Preserving Image Generation

Deep learning models are found to be vulnerable to adversarial examples,...
08/01/2016

Early Methods for Detecting Adversarial Images

Many machine learning classifiers are vulnerable to adversarial perturba...
09/27/2019

Maximal adversarial perturbations for obfuscation: Hiding certain attributes while preserving rest

In this paper we investigate the usage of adversarial perturbations for ...
03/07/2019

Attack Type Agnostic Perceptual Enhancement of Adversarial Images

Adversarial images are samples that are intentionally modified to deceiv...
06/19/2018

Maximally Invariant Data Perturbation as Explanation

While several feature scoring methods are proposed to explain the output...