On the Robustness of Deep K-Nearest Neighbors

03/20/2019
by   Chawin Sitawarin, et al.
18

Despite a large amount of attention on adversarial examples, very few works have demonstrated an effective defense against this threat. We examine Deep k-Nearest Neighbor (DkNN), a proposed defense that combines k-Nearest Neighbor (kNN) and deep learning to improve the model's robustness to adversarial examples. It is challenging to evaluate the robustness of this scheme due to a lack of efficient algorithm for attacking kNN classifiers with large k and high-dimensional data. We propose a heuristic attack that allows us to use gradient descent to find adversarial examples for kNN classifiers, and then apply it to attack the DkNN defense as well. Results suggest that our attack is moderately stronger than any naive attack on kNN and significantly outperforms other attacks on DkNN.

READ FULL TEXT

page 1

page 6

research
03/13/2021

Attack as Defense: Characterizing Adversarial Examples using Robustness

As a new programming paradigm, deep learning has expanded its applicatio...
research
07/26/2018

Evaluating and Understanding the Robustness of Adversarial Logit Pairing

We evaluate the robustness of Adversarial Logit Pairing, a recently prop...
research
11/15/2019

AdvKnn: Adversarial Attacks On K-Nearest Neighbor Classifiers With Approximate Gradients

Deep neural networks have been shown to be vulnerable to adversarial exa...
research
06/13/2017

Analyzing the Robustness of Nearest Neighbors to Adversarial Examples

Motivated by applications such as autonomous vehicles, test-time attacks...
research
11/19/2020

Adversarial Examples for k-Nearest Neighbor Classifiers Based on Higher-Order Voronoi Diagrams

Adversarial examples are a widely studied phenomenon in machine learning...
research
03/05/2019

Defense Against Adversarial Images using Web-Scale Nearest-Neighbor Search

A plethora of recent work has shown that convolutional networks are not ...
research
06/27/2021

ASK: Adversarial Soft k-Nearest Neighbor Attack and Defense

K-Nearest Neighbor (kNN)-based deep learning methods have been applied t...

Please sign up or login with your details

Forgot password? Click here to reset