Skip to Main Content
HBS Home
  • About
  • Academic Programs
  • Alumni
  • Faculty & Research
  • Baker Library
  • Giving
  • Harvard Business Review
  • Initiatives
  • News
  • Recruit
  • Map / Directions
Faculty & Research
  • Faculty
  • Research
  • Featured Topics
  • Academic Units
  • …→
  • Harvard Business School→
  • Faculty & Research→
Publications
Publications
  • 2022
  • Article
  • Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI)

Data Poisoning Attacks on Off-Policy Evaluation Methods

By: Elita Lobo, Harvineet Singh, Marek Petrik, Cynthia Rudin and Himabindu Lakkaraju
  • Format:Print
  • | Pages:11
ShareBar

Abstract

Off-policy Evaluation (OPE) methods are a crucial tool for evaluating policies in high-stakes domains such as healthcare, where exploration is often infeasible, unethical, or expensive. However, the extent to which such methods can be trusted under adversarial threats to data quality is largely unexplored. In this work, we make the first attempt at investigating the sensitivity of OPE methods to marginal adversarial perturbations to the data. We design a generic data poisoning attack framework leveraging influence functions from robust statistics to carefully construct perturbations that maximize error in the policy value estimates. We carry out extensive experimentation with multiple healthcare and control datasets. Our results demonstrate that many existing OPE methods are highly prone to generating value estimates with large errors when subject to data poisoning attacks, even for small adversarial perturbations. These findings question the reliability of policy values derived using OPE methods and motivate the need for developing OPE methods that are statistically robust to train-time data poisoning attacks.

Keywords

Analytics and Data Science; Cybersecurity; Mathematical Methods

Citation

Lobo, Elita, Harvineet Singh, Marek Petrik, Cynthia Rudin, and Himabindu Lakkaraju. "Data Poisoning Attacks on Off-Policy Evaluation Methods." Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI) 38th (2022): 1264–1274.
  • Read Now

About The Author

Himabindu Lakkaraju

Technology and Operations Management
→More Publications

More from the Authors

    • 2023
    • Proceedings of the International Conference on Machine Learning (ICML)

    On the Impact of Actionable Explanations on Social Segregation

    By: Ruijiang Gao and Himabindu Lakkaraju
    • 2023
    • Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI)

    On Minimizing the Impact of Dataset Shifts on Actionable Explanations

    By: Anna Meyer, Dan Ley, Suraj Srinivas and Himabindu Lakkaraju
    • 2023
    • Proceedings of the International Conference on Machine Learning (ICML)

    Towards Bridging the Gaps between the Right to Explanation and the Right to Be Forgotten

    By: Himabindu Lakkaraju, Satyapriya Krishna and Jiaqi Ma
More from the Authors
  • On the Impact of Actionable Explanations on Social Segregation By: Ruijiang Gao and Himabindu Lakkaraju
  • On Minimizing the Impact of Dataset Shifts on Actionable Explanations By: Anna Meyer, Dan Ley, Suraj Srinivas and Himabindu Lakkaraju
  • Towards Bridging the Gaps between the Right to Explanation and the Right to Be Forgotten By: Himabindu Lakkaraju, Satyapriya Krishna and Jiaqi Ma
ǁ
Campus Map
Harvard Business School
Soldiers Field
Boston, MA 02163
→Map & Directions
→More Contact Information
  • Make a Gift
  • Site Map
  • Jobs
  • Harvard University
  • Trademarks
  • Policies
  • Accessibility
  • Digital Accessibility
Copyright © President & Fellows of Harvard College