no code implementations • 23 Jan 2024 • Longkun Guo, Chaoqi Jia, Kewen Liao, Zhigang Lu, Minhui Xue
Center-based clustering has attracted significant research interest from both theory and practice.
no code implementations • 4 Oct 2023 • Hassan Jameel Asghar, Zhigang Lu, Zhongrui Zhao, Dali Kaafar
In this work, we construct an interactive protocol for this problem based on the fully homomorphic encryption scheme over the Torus (TFHE) and label differential privacy, where the underlying machine learning model is a neural network.
no code implementations • 7 Sep 2023 • Aoting Hu, Zhigang Lu, Renjie Xie, Minhui Xue
(2) We introduce a novel approach using less private samples to enhance the performance of ownership testing.
no code implementations • 3 Apr 2022 • Zhigang Lu, Hassan Jameel Asghar, Mohamed Ali Kaafar, Darren Webb, Peter Dickinson
Under a black-box setting, based on this global sensitivity, to control the overall noise injection, we propose a novel output perturbation framework by injecting DP noise into a randomly sampled neuron (via the exponential mechanism) at the output layer of a baseline non-private neural network trained with a convexified loss function.
1 code implementation • 17 Feb 2020 • Shakila Mahjabin Tonni, Dinusha Vatsalan, Farhad Farokhi, Dali Kaafar, Zhigang Lu, Gioacchino Tangari
Our results reveal the relationship between MIA accuracy and properties of the dataset and training model in use.
no code implementations • 3 Feb 2020 • Zhigang Lu, Hong Shen
This problem severely impacts the clustering quality and the efficiency of a differentially private algorithm.