Towards A Proactive ML Approach for Detecting Backdoor Poison Samples

Xiangyu Qi, Tinghao Xie, Jiachen T. Wang, Tong Wu, Saeed Mahloujifar, Prateek Mittal

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Adversaries can embed backdoors in deep learning models by introducing backdoor poison samples into training datasets. In this work, we investigate how to detect such poison samples to mitigate the threat of backdoor attacks. First, we uncover a post-hoc workflow underlying most prior work, where defenders passively allow the attack to proceed and then leverage the characteristics of the post-attacked model to uncover poison samples. We reveal that this workflow does not fully exploit defenders’ capabilities, and defense pipelines built on it are prone to failure or performance degradation in many scenarios. Second, we suggest a paradigm shift by promoting a proactive mindset in which defenders engage proactively with the entire model training and poison detection pipeline, directly enforcing and magnifying distinctive characteristics of the post-attacked model to facilitate poison detection. Based on this, we formulate a unified framework and provide practical insights on designing detection pipelines that are more robust and generalizable. Third, we introduce the technique of Confusion Training (CT) as a concrete instantiation of our framework. CT applies an additional poisoning attack to the already poisoned dataset, actively decoupling benign correlation while exposing backdoor patterns to detection. Empirical evaluations on 4 datasets and 14 types of attacks validate the superiority of CT over 14 baseline defenses.1

Original languageEnglish (US)
Title of host publication32nd USENIX Security Symposium, USENIX Security 2023
PublisherUSENIX Association
Pages1685-1702
Number of pages18
ISBN (Electronic)9781713879497
StatePublished - 2023
Event32nd USENIX Security Symposium, USENIX Security 2023 - Anaheim, United States
Duration: Aug 9 2023Aug 11 2023

Publication series

Name32nd USENIX Security Symposium, USENIX Security 2023
Volume3

Conference

Conference32nd USENIX Security Symposium, USENIX Security 2023
Country/TerritoryUnited States
CityAnaheim
Period8/9/238/11/23

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'Towards A Proactive ML Approach for Detecting Backdoor Poison Samples'. Together they form a unique fingerprint.

Cite this