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

## TL;DR

This paper demonstrates that CNN-based edge detection models are vulnerable to adversarial examples that can cause them to fail or hallucinate edges, and these adversarial attacks transfer to other vision models, affecting their accuracy.

## Contribution

It reveals the existence and transferability of adversarial examples in edge detection CNNs, highlighting a new vulnerability in low-level vision tasks.

## Key findings

- Adversarial perturbations cause edge detection failures and hallucinations.
- Adversarial examples transfer to other CNN models like classifiers and segmenters.
- Attacks significantly reduce the accuracy of various vision models.

## Abstract

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.