Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks

TL;DR

This paper introduces targeted clean-label poisoning attacks on neural networks, demonstrating how a single or multiple poisoned images can manipulate classifier behavior without affecting overall accuracy.

Contribution

The paper presents novel optimization-based methods for creating clean-label poisons that are effective in transfer learning and end-to-end training scenarios.

Findings

Single poison images can control classifier behavior in transfer learning.

Multiple poisoned instances increase reliability in end-to-end training.

Poisoned frog images successfully manipulated image classifiers.

Abstract

Data poisoning is an attack on machine learning models wherein the attacker adds examples to the training set to manipulate the behavior of the model at test time. This paper explores poisoning attacks on neural nets. The proposed attacks use "clean-labels"; they don't require the attacker to have any control over the labeling of training data. They are also targeted; they control the behavior of the classifier on a $\textit{specific}$ test instance without degrading overall classifier performance. For example, an attacker could add a seemingly innocuous image (that is properly labeled) to a training set for a face recognition engine, and control the identity of a chosen person at test time. Because the attacker does not need to control the labeling function, poisons could be entered into the training set simply by leaving them on the web and waiting for them to be scraped by a data collection bot. We present an optimization-based method for crafting poisons, and show that just one single poison image can control classifier behavior when transfer learning is used. For full end-to-end training, we present a "watermarking" strategy that makes poisoning reliable using multiple ($\approx$50) poisoned training instances. We demonstrate our method by generating poisoned frog images from the CIFAR dataset and using them to manipulate image classifiers.