XRAND: Differentially Private Defense against Explanation-Guided Attacks
Document Type
Conference Proceeding
Publication Date
6-27-2023
Abstract
Recent development in the field of explainable artificial intelligence (XAI) has helped improve trust in Machine-Learning-as-a-Service (MLaaS) systems, in which an explanation is provided together with the model prediction in response to each query. However, XAI also opens a door for adversaries to gain insights into the black-box models in MLaaS, thereby making the models more vulnerable to several attacks. For example, feature-based explanations (e.g., SHAP) could expose the top important features that a black-box model focuses on. Such disclosure has been exploited to craft effective backdoor triggers against malware classifiers. To address this trade-off, we introduce a new concept of achieving local differential privacy (LDP) in the explanations, and from that we establish a defense, called XRAND, against such attacks. We show that our mechanism restricts the information that the adversary can learn about the top important features, while maintaining the faithfulness of the explanations.
Identifier
85168249381 (Scopus)
ISBN
[9781577358800]
Publication Title
Proceedings of the 37th Aaai Conference on Artificial Intelligence Aaai 2023
External Full Text Location
https://doi.org/10.1609/aaai.v37i10.2636126401
First Page
11873
Last Page
11881
Volume
37
Grant
IIS-2123809
Fund Ref
National Science Foundation
Recommended Citation
Nguyen, Truc; Lai, Phung; Phan, Hai; and Thai, My T., "XRAND: Differentially Private Defense against Explanation-Guided Attacks" (2023). Faculty Publications. 1630.
https://digitalcommons.njit.edu/fac_pubs/1630