Provable stability defenses for targeted data poisoning

Vijitbenjaronk, Warut D.

Permalink

https://hdl.handle.net/2142/108638 Copy

Description

Title

Provable stability defenses for targeted data poisoning

Author(s)

Vijitbenjaronk, Warut D.

Issue Date

2020-07-22

Director of Research (if dissertation) or Advisor (if thesis)

Koyejo, Oluwasanmi

Department of Study

Computer Science

Discipline

Computer Science

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Date of Ingest

2020-10-07T22:44:46Z

Keyword(s)

• data poisoning
• machine learning
• robust machine learning
• stable support vector machine
• algorithmic stability
• uniform stability
• adversarial machine learning

Abstract

Modern machine learning systems are often trained on massive, crowdsourced datasets. Due to the impossibility of checking this data, these systems may be susceptible to data poisoning attacks where malicious users inject false training data in order to influence the learned model. While recent work has focused primarily on the untargeted case, where the attacker's goal is to increase overall error, much less is understood about the theoretical underpinnings of targeted data poisoning attacks. These attacks try to cause the learned model to change its prediction on only a few targeted examples without raising suspicion. We suggest algorithmic stability as a sufficient condition for robustness against data poisoning, construct upper bounds on the possible effectiveness of data poisoning attacks against stable algorithms, and propose an algorithm that provides resilience against popular classes of attacks. Empirically, we report findings on the MNIST 1-7 image classification dataset and the TREC 2007 spam detection dataset that confirms our theoretical findings.

Graduation Semester

2020-08

Type of Resource

Thesis

Permalink

http://hdl.handle.net/2142/108638

Copyright and License Information

Copyright 2020 Warut D. Vijitbenjaronk

Owning Collections