{"title":"Proving data-poisoning robustness in decision trees","authors":"Samuel Drews, Aws Albarghouthi, Loris D'antoni","doi":"10.1145/3385412.3385975","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":20580,"journal":{"name":"Proceedings of the 41st ACM SIGPLAN Conference on Programming Language Design and Implementation","volume":"39 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2019-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"14","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 41st ACM SIGPLAN Conference on Programming Language Design and Implementation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3385412.3385975","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 14
Abstract
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.