论文标题
用于机器学习的数据集安全：数据中毒，后门攻击和防御
Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses
论文作者
论文摘要
随着机器学习系统规模的增长，他们的培训数据需求也会增加，迫使从业人员自动化和外包培训数据的策划，以实现最先进的绩效。对数据收集过程的缺乏值得信赖的人类监督会使组织面临安全漏洞；可以操纵培训数据以控制和降低学习模型的下游行为。这项工作的目的是系统地对并讨论各种数据集漏洞和利用，防御这些威胁的方法以及在该领域的一系列开放问题。除了描述各种中毒和后门威胁模型及其之间的关系外，我们还发展了他们的统一分类法。
As machine learning systems grow in scale, so do their training data requirements, forcing practitioners to automate and outsource the curation of training data in order to achieve state-of-the-art performance. The absence of trustworthy human supervision over the data collection process exposes organizations to security vulnerabilities; training data can be manipulated to control and degrade the downstream behaviors of learned models. The goal of this work is to systematically categorize and discuss a wide range of dataset vulnerabilities and exploits, approaches for defending against these threats, and an array of open problems in this space. In addition to describing various poisoning and backdoor threat models and the relationships among them, we develop their unified taxonomy.
