Adversarial Examples Make Strong Poisons

06/21/2021
by   Liam Fowl, et al.
7

The adversarial machine learning literature is largely partitioned into evasion attacks on testing data and poisoning attacks on training data. In this work, we show that adversarial examples, originally intended for attacking pre-trained models, are even more effective for data poisoning than recent methods designed specifically for poisoning. Our findings indicate that adversarial examples, when assigned the original label of their natural base image, cannot be used to train a classifier for natural images. Furthermore, when adversarial examples are assigned their adversarial class label, they are useful for training. This suggests that adversarial examples contain useful semantic content, just with the “wrong” labels (according to a network, but not a human). Our method, adversarial poisoning, is substantially more effective than existing poisoning methods for secure dataset release, and we release a poisoned version of ImageNet, ImageNet-P, to encourage research into the strength of this form of data obfuscation.

READ FULL TEXT

page 6

page 9

page 14

page 17

research
07/16/2019

Natural Adversarial Examples

We introduce natural adversarial examples -- real-world, unmodified, and...
research
03/28/2018

The Effects of JPEG and JPEG2000 Compression on Attacks using Adversarial Examples

Adversarial examples are known to have a negative effect on the performa...
research
11/22/2021

Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classes

Although ImageNet was initially proposed as a dataset for performance be...
research
03/18/2020

Fixing the train-test resolution discrepancy: FixEfficientNet

This note complements the paper "Fixing the train-test resolution discre...
research
02/23/2021

Rethinking Natural Adversarial Examples for Classification Models

Recently, it was found that many real-world examples without intentional...
research
11/21/2018

How the Softmax Output is Misleading for Evaluating the Strength of Adversarial Examples

Even before deep learning architectures became the de facto models for c...
research
12/01/2016

A Theoretical Framework for Robustness of (Deep) Classifiers against Adversarial Examples

Most machine learning classifiers, including deep neural networks, are v...

Please sign up or login with your details

Forgot password? Click here to reset