Indirect Local Attacks for Context-aware Semantic Segmentation Networks

11/29/2019
by   Krishna Kanth Nakka, et al.
7

Recently, deep networks have achieved impressive semantic segmentation performance, in particular thanks to their use of larger contextual information. In this paper, we show that the resulting networks are sensitive not only to global attacks, where perturbations affect the entire input image, but also to indirect local attacks where perturbations are confined to a small image region that does not overlap with the area that we aim to fool. To this end, we introduce several indirect attack strategies, including adaptive local attacks, aiming to find the best image location to perturb, and universal local attacks. Furthermore, we propose attack detection techniques both for the global image level and to obtain a pixel-wise localization of the fooled regions. Our results are unsettling: Because they exploit a larger context, more accurate semantic segmentation networks are more sensitive to indirect local attacks.

READ FULL TEXT

page 7

page 8

page 20

page 21

page 22

page 23

page 26

page 27

research
03/17/2021

CAP: Context-Aware Pruning for Semantic Segmentation

Network pruning for deep convolutional neural networks (CNNs) has recent...
research
08/16/2020

Context-aware Feature Generation for Zero-shot Semantic Segmentation

Existing semantic segmentation models heavily rely on dense pixel-wise a...
research
07/18/2018

Location Augmentation for CNN

CNNs have made a tremendous impact on the field of computer vision in th...
research
02/04/2023

CosPGD: a unified white-box adversarial attack for pixel-wise prediction tasks

While neural networks allow highly accurate predictions in many tasks, t...
research
03/23/2017

Self corrective Perturbations for Semantic Segmentation and Classification

Convolutional Neural Networks have been a subject of great importance ov...
research
06/14/2022

Proximal Splitting Adversarial Attacks for Semantic Segmentation

Classification has been the focal point of research on adversarial attac...
research
08/03/2021

Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation

In this paper, we tackle the detection of out-of-distribution (OOD) obje...

Please sign up or login with your details

Forgot password? Click here to reset