Megex: Data-free model extraction attack against gradient-based explainable ai

T Miura, T Shibahara, N Yanai - Proceedings of the 2nd ACM Workshop …, 2024 - dl.acm.org
Explainable AI encourages machine learning applications in the real world, whereas data-
free model extraction attacks (DFME), in which an adversary steals a trained machine …

[图书][B] Security and Privacy in Federated Learning

S Yu, L Cui - 2023 - Springer
In the recent two decades, we have witnessed the dramatic development of artificial
intelligence (AI in short), not only in artificial intelligence itself but also its applications in …

Disguide: Disagreement-guided data-free model extraction

J Rosenthal, E Enouen, HV Pham, L Tan - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Recent model-extraction attacks on Machine Learning as a Service (MLaaS) systems have
moved towards data-free approaches, showing the feasibility of stealing models trained with …

A taxonomic survey of model extraction attacks

D Genç, M Özuysal, E Tomur - 2023 IEEE International …, 2023 - ieeexplore.ieee.org
A model extraction attack aims to clone a machine learning target model deployed in the
cloud solely by querying the target in a black-box manner. Once a clone is obtained it is …

Inference Attacks and Counterattacks in Federated Learning

S Yu, L Cui - Security and Privacy in Federated Learning, 2022 - Springer
From the previous chapter, we have learned that federated learning (FL) can be used to
protect data privacy since users no longer share their raw data during collaborative training …