Identification of the Adversary from a Single Adversarial Example

Minhao Cheng, Rui Min, Haochen Sun, Pin Yu Chen

Research output: Contribution to journalConference articlepeer-review

Abstract

Deep neural networks have been shown vulnerable to adversarial examples. Even though many defense methods have been proposed to enhance the robustness, it is still a long way toward providing an attack-free method to build a trustworthy machine learning system. In this paper, instead of enhancing the robustness, we take the investigator's perspective and propose a new framework to trace the first compromised model copy in a forensic investigation manner. Specifically, we focus on the following setting: the machine learning service provider provides model copies for a set of customers. However, one of the customers conducted adversarial attacks to fool the system. Therefore, the investigator's objective is to identify the first compromised copy by collecting and analyzing evidence from only available adversarial examples. To make the tracing viable, we design a random mask watermarking mechanism to differentiate adversarial examples from different copies. First, we propose a tracing approach in the data-limited case where the original example is also available. Then, we design a data-free approach to identify the adversary without accessing the original example. Finally, the effectiveness of our proposed framework is evaluated by extensive experiments with different model architectures, adversarial attacks, and datasets. Our code is publicly available at https://github.com/rmin2000/adv_tracing.git.

Original languageEnglish (US)
Pages (from-to)5472-5484
Number of pages13
JournalProceedings of Machine Learning Research
Volume202
StatePublished - 2023
Event40th International Conference on Machine Learning, ICML 2023 - Honolulu, United States
Duration: Jul 23 2023Jul 29 2023

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability

Cite this