Adversarial Examples for Edge Detection: They Exist, and They Transfer

06/02/2019
by   Christian Cosgrove, et al.
0

Convolutional neural networks have recently advanced the state of the art in many tasks including edge and object boundary detection. However, in this paper, we demonstrate that these edge detectors inherit a troubling property of neural networks: they can be fooled by adversarial examples. We show that adding small perturbations to an image causes HED, a CNN-based edge detection model, to fail to locate edges, to detect nonexistent edges, and even to hallucinate arbitrary configurations of edges. More surprisingly, we find that these adversarial examples transfer to other CNN-based vision models. In particular, attacks on edge detection result in significant drops in accuracy in models trained to perform unrelated, high-level tasks like image classification and semantic segmentation. Our code will be made public.

READ FULL TEXT

page 1

page 4

page 8

research
03/24/2017

Adversarial Examples for Semantic Segmentation and Object Detection

It has been well demonstrated that adversarial examples, i.e., natural i...
research
10/11/2018

Characterizing Adversarial Examples Based on Spatial Consistency Information for Semantic Segmentation

Deep Neural Networks (DNNs) have been widely applied in various recognit...
research
11/22/2019

Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion Reduction

Neural networks are known to be vulnerable to carefully crafted adversar...
research
09/17/2019

Enhancing JPEG Steganography using Iterative Adversarial Examples

Convolutional Neural Networks (CNN) based methods have significantly imp...
research
07/10/2020

Miss the Point: Targeted Adversarial Attack on Multiple Landmark Detection

Recent methods in multiple landmark detection based on deep convolutiona...
research
05/19/2020

Synthesizing Unrestricted False Positive Adversarial Objects Using Generative Models

Adversarial examples are data points misclassified by neural networks. O...
research
03/29/2018

Weakening the Detecting Capability of CNN-based Steganalysis

Recently, the application of deep learning in steganalysis has drawn man...

Please sign up or login with your details

Forgot password? Click here to reset