The TrojAI Software Framework: An OpenSource tool for Embedding Trojans into Deep Learning Models

In this paper, we introduce the TrojAI software framework, an open source set of Python tools capable of generating triggered (poisoned) datasets and associated deep learning (DL) models with trojans at scale. We utilize the developed framework to generate a large set of trojaned MNIST classifiers,...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-03
Main Authors: Karra, Kiran, Ashcraft, Chace, Fendley, Neil
Format: Article
Language:English
Subjects:
Anomalies
Datasets
Deep learning
Embedding
Machine learning
Malware
Software
Training
Workflow
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we introduce the TrojAI software framework, an open source set of Python tools capable of generating triggered (poisoned) datasets and associated deep learning (DL) models with trojans at scale. We utilize the developed framework to generate a large set of trojaned MNIST classifiers, as well as demonstrate the capability to produce a trojaned reinforcement-learning model using vector observations. Results on MNIST show that the nature of the trigger, training batch size, and dataset poisoning percentage all affect successful embedding of trojans. We test Neural Cleanse against the trojaned MNIST models and successfully detect anomalies in the trained models approximately \(18\%\) of the time. Our experiments and workflow indicate that the TrojAI software framework will enable researchers to easily understand the effects of various configurations of the dataset and training hyperparameters on the generated trojaned deep learning model, and can be used to rapidly and comprehensively test new trojan detection methods.
ISSN:2331-8422