FedPass: Privacy-Preserving Vertical Federated Deep Learning with Adaptive Obfuscation

Authors: Hanlin Gu, Jiahuan Luo, Yan Kang, Lixin Fan, Qiang Yang

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experimental result s with different datasets and network architectures also justify the superiority of Fed Pass against existing methods in light of its near-optimal tradeoff between privacy and model performance.
Researcher Affiliation Collaboration Hanlin Gu1 , Jiahuan Luo1 , Yan Kang1 , Lixin Fan1 and Qiang Yang1,2 1Webank, China 2Hong Kong University of Science and Technology, Hong Kong
Pseudocode Yes Algorithm 1 Fed Pass; Algorithm 2 Adaptive Obfuscation (g())
Open Source Code No The paper does not provide any explicit statements or links to open-source code for the described methodology.
Open Datasets Yes We conduct experiments on three datasets: MNIST [Le Cun et al., 2010], CIFAR10 [Krizhevsky et al., 2014] and Model Net [Wu et al., 2015].
Dataset Splits No The paper uses standard datasets but does not explicitly provide specific train/validation/test split percentages, sample counts, or clear references to how these datasets were partitioned for the experiments.
Hardware Specification No The paper does not provide specific details about the hardware used for running the experiments, such as GPU/CPU models, memory, or cloud computing instances.
Software Dependencies No The paper does not specify version numbers for any software dependencies, libraries, or programming languages used in the experiments.
Experiment Setup Yes For Fed Pass, the range of the mean of Gaussian distribution N is from 2 to 200, the variance is from 1 to 64. Passports are embedded in the last convolution layer of the passive party s model and first fully connected layer of the active party s model. ... Input: Communication rounds T, Passive parties number K, learning rate η, batch size b, the passport range and variance {N a, σa} and {N pk, σpk} for the active party and passive party k respectively...