Abstract Deep Neural Network (DNN), one of the most powerful machine learning algorithms, is increasingly leveraged to overcome the bottleneck of effectively exploring and …
J Zhang, S Peng, Y Gao, Z Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Training a Deep Learning (DL) model requires proprietary data and computing-intensive resources. To recoup their training costs, a model provider can monetize DL models through …
N Lukas, E Jiang, X Li… - 2022 IEEE Symposium on …, 2022 - ieeexplore.ieee.org
Deep Neural Network (DNN) watermarking is a method for provenance verification of DNN models. Watermarking should be robust against watermark removal attacks that derive a …
BGA Tekgul, Y Xia, S Marchal… - 2021 40th International …, 2021 - ieeexplore.ieee.org
Federated learning is a distributed learning technique where machine learning models are trained on client devices in which the local training data resides. The training is coordinated …
Abstract Data-Free Model Extraction (DFME) aims to clone a black-box model without knowing its original training data distribution, making it much easier for attackers to steal …
U Aïvodji, A Bolot, S Gambs - arXiv preprint arXiv:2009.01884, 2020 - arxiv.org
Post-hoc explanation techniques refer to a posteriori methods that can be used to explain how black-box machine learning models produce their outcomes. Among post-hoc …
Creating a state-of-the-art deep-learning system requires vast amounts of data, expertise, and hardware, yet research into copyright protection for neural networks has been limited …
Z Zhang, Y Chen, D Wagner - Proceedings of the 14th ACM Workshop …, 2021 - dl.acm.org
Given black-box access to the prediction API, model extraction attacks can steal the functionality of models deployed in the cloud. In this paper, we introduce the SEAT detector …
The prosperity of AI and edge computing has pushed more and more well-trained DNN models to be deployed on third-party edge devices to compose mission-critical applications …