Purdue University Graduate School
Browse

RANKED CLUSTER INFLUENCE: A DEFENSE AGAINST ADVERSARIAL LABELING ATTACKS ON FAIRNESS

thesis
posted on 2025-04-26, 21:01 authored by Athreyan Mohana Krishnan SangeethaAthreyan Mohana Krishnan Sangeetha

Adversarial Labeling Attacks are a proven method of degrading model metrics by flipping the labels of points in the training set or adding copies/imitations of points with the flipped label. The proposed idea is to identify the poisoned data points i.e. flipped data points using influence functions. Former ideas explored how perturbing the features of a data point in the training set influenced the loss calculation for the testing set. Now we see how perturbing the target aka flipping the label affects the loss calculation on the testing set and if we can identify the poisoned points.

History

Degree Type

  • Master of Science

Department

  • Computer and Information Technology

Campus location

  • West Lafayette

Advisor/Supervisor/Committee Chair

Baijian Yang

Additional Committee Member 2

Romila Pradhan

Additional Committee Member 3

Tawfiq Salem

Usage metrics

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC