Sign In

Communications of the ACM

Research Highlights

Proving Data-Poisoning Robustness in Decision Trees

decision tree, illustration

Credit: Getty Images

Machine learning models are brittle, and small changes in the training data can result in different predictions. We study the problem of proving that a prediction is robust to data poisoning, where an attacker can inject a number of malicious elements into the training set to influence the learned model. We target decision tree models, a popular and simple class of machine learning models that underlies many complex learning techniques. We present a sound verification technique based on abstract interpretation and implement it in a tool called Antidote. Antidote abstractly trains decision trees for an intractably large space of possible poisoned datasets. Due to the soundness of our abstraction, Antidote can produce proofs that, for a given input, the corresponding prediction would not have changed had the training set been tampered with or not. We demonstrate the effectiveness of Antidote on a number of popular datasets.

Back to Top

1. Introduction

Artificial intelligence, in the form of machine learning (ML), is rapidly transforming the world as we know it. Today, ML is responsible for an ever-growing spectrum of sensitive decisions—from loan decisions, to diagnosing diseases, to autonomous driving. Many recent works have shown how ML models are brittle,2,5,19,20,22 and with ML spreading across many industries, the issue of robustness in ML models has taken center stage. The research field that deals with studying robustness of ML models is referred to as adversarial machine learning. In this field, researchers have proposed many definitions that try to capture robustness to different adversaries. The majority of these works have focused on verifying or improving the model's robustness to test-time attacks,8,9,21 where an adversary can craft small perturbations to input examples that fool the ML model into changing its prediction, for example, making the model think a picture of a cat is that of a zebra.4


No entries found

Log in to Read the Full Article

Sign In

Sign in using your ACM Web Account username and password to access premium content if you are an ACM member, Communications subscriber or Digital Library subscriber.

Need Access?

Please select one of the options below for access to premium content and features.

Create a Web Account

If you are already an ACM member, Communications subscriber, or Digital Library subscriber, please set up a web account to access premium content on this site.

Join the ACM

Become a member to take full advantage of ACM's outstanding computing information resources, networking opportunities, and other benefits.

Subscribe to Communications of the ACM Magazine

Get full access to 50+ years of CACM content and receive the print version of the magazine monthly.

Purchase the Article

Non-members can purchase this article or a copy of the magazine in which it appears.