Connecting the Dots: Detecting Adversarial Perturbations Using Context Inconsistency

07/19/2020
by   Shasha Li, et al.
10

There has been a recent surge in research on adversarial perturbations that defeat Deep Neural Networks (DNNs) in machine vision; most of these perturbation-based attacks target object classifiers. Inspired by the observation that humans are able to recognize objects that appear out of place in a scene or along with other unlikely objects, we augment the DNN with a system that learns context consistency rules during training and checks for the violations of the same during testing. Our approach builds a set of auto-encoders, one for each object class, appropriately trained so as to output a discrepancy between the input and output if an added adversarial perturbation violates context consistency rules. Experiments on PASCAL VOC and MS COCO show that our method effectively detects various adversarial attacks and achieves high ROC-AUC (over 0.95 in most cases); this corresponds to over 20 improvement over a state-of-the-art context-agnostic method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/12/2019

Robust Design of Deep Neural Networks against Adversarial Attacks based on Lyapunov Theory

Deep neural networks (DNNs) are vulnerable to subtle adversarial perturb...
research
11/15/2019

Simple iterative method for generating targeted universal adversarial perturbations

Deep neural networks (DNNs) are vulnerable to adversarial attacks. In pa...
research
12/21/2017

ReabsNet: Detecting and Revising Adversarial Examples

Though deep neural network has hit a huge success in recent studies and ...
research
11/16/2017

Defense against Universal Adversarial Perturbations

Recent advances in Deep Learning show the existence of image-agnostic qu...
research
08/23/2021

Multi-Expert Adversarial Attack Detection in Person Re-identification Using Context Inconsistency

The success of deep neural networks (DNNs) haspromoted the widespread ap...
research
09/12/2022

Adaptive Perturbation Generation for Multiple Backdoors Detection

Extensive evidence has demonstrated that deep neural networks (DNNs) are...
research
03/02/2022

Detecting Adversarial Perturbations in Multi-Task Perception

While deep neural networks (DNNs) achieve impressive performance on envi...

Please sign up or login with your details

Forgot password? Click here to reset