The TrojAI Software Framework：一个用于将木马嵌入深度学习模型的OpenSource工具
The TrojAI Software Framework: An OpenSource tool for Embedding Trojans into Deep Learning Models
摘要：
在本文中，我们介绍了TrojAI软件框架，这是一组开源的Python工具，能够生成触发（中毒）数据集和相关的深度学习（DL）模型。我们利用开发的框架来生成一个大型的木马MNIST分类器，以及演示的能力，产生一个木马的识别学习模型，使用向量观测。MNIST的结果表明，触发器的性质，训练批量大小和数据集中毒百分比都影响木马的成功嵌入。我们针对安装了木马的MNIST模型测试了Neural Cleanse，并在大约$18\%$的时间内成功检测到训练模型中的异常。我们的实验和工作流程表明，TrojAI软件框架将使研究人员能够轻松了解数据集和训练超参数的各种配置对生成的木马深度学习模型的影响，并可用于快速全面地测试新的木马检测方法。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
