Back to search

NJIT

Un-fair trojan: Targeted backdoor attacks against model fairness

Abstract

dc:description.abstract

<p>Machine learning models have been shown to be vulnerable against various backdoor and data poisoning attacks that adversely affect model behavior. Additionally, these attacks have been shown to make unfair predictions with respect to certain protected features. In federated learning, multiple local models contribute to a single global model communicating only using local gradients, the issue of attacks become more prevalent and complex. Previously published works revolve around solving these issues both individually and jointly. However, there has been little study on the effects of attacks against model fairness. Demonstrated in this work, a flexible attack, which we call Un-Fair Trojan, that targets model fairness while remaining stealthy can have devastating effects against machine learning models.</p>

Degree

thesis:*
Name thesis:degree_name
Master of Science in Computer Engineering - (M.S.)
Discipline thesis:degree_discipline
Electrical and Computer Engineering

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Furth, Nicholas
Contributors dc:contributor
  • Abdallah Khreishah
  • Cong Wang
  • Hai Nhat Phan

Subjects

dc:subject × 8

Identifiers

dc:identifier.*
Repository record dc:identifier
https://digitalcommons.njit.edu/theses/1996

Chain of custody

source
Harvested from
NJIT
Base URL
digitalcommons.njit.edu/do/oai/
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Furth, Nicholas. Un-fair trojan: Targeted backdoor attacks against model fairness. https://digitalcommons.njit.edu/theses/1996