• Publications
  • Influence
Randomizing Social Networks: a Spectrum Preserving Approach
TLDR
A spectrum preserving graph randomization method is presented which can better preserve network properties while protecting edge anonymity, and is empirically evaluated and theoretical analysis on the extent to which edge anonymity can be achieved.
SNE: Signed Network Embedding
TLDR
The signed network embedding model called SNE adopts the log-bilinear model, uses node representations of all nodes along a given path, and further incorporates two signed-type vectors to capture the positive or negative relationship of each edge along the path.
One-Class Adversarial Nets for Fraud Detection
TLDR
Experimental results show that the OCAN outperforms the state-of-the-art one-class classification models and achieves comparable performance with the latest multi-source LSTM model that requires both benign and malicious users in the training phase.
Differential Privacy Preserving Spectral Graph Analysis
TLDR
It is proved that the sampling procedure achieves differential privacy and the two approaches to computing the e-differential eigen decomposition of the graph’s adjacency matrix under the same differential privacy threshold.
FairGAN: Fairness-aware Generative Adversarial Networks
TLDR
This paper presents fairness-aware generative adversarial networks, called FairGAN, which are able to learn a generator producing fair data and also preserving good data utility, and further ensures the classifiers which are trained on generated data can achieve fair classification on real data.
Adaptive Laplace Mechanism: Differential Privacy Preservation in Deep Learning
TLDR
A novel mechanism to preserve differential privacy in deep neural networks, such that the privacy budget consumption is totally independent of the number of training steps, and it has the ability to adaptively inject noise into features based on the contribution of each to the output.
Guided test generation for database applications via synthesized database interactions
TLDR
An approach called SynDB is proposed that synthesizes new database interactions to replace the original ones from the database application under test that can achieve higher code coverage than existing test generation approaches for database applications.
A Causal Framework for Discovering and Removing Direct and Indirect Discrimination
TLDR
This paper proposes an effective algorithm for discovering direct and indirect discrimination, as well as an algorithm for precisely removing both types of discrimination while retaining good data utility.
A Survey of Privacy-Preservation of Graphs and Social Networks
TLDR
This chapter surveys the very recent research development on privacy preserving publishing of graphs and social network data, and categorizes the state-of-the-art anonymization methods on simple graphs in three main categories: K-anonymity based privacy Preservation via edge modification, probabilistic privacy preservation via edge randomization, and privacy preservation through generalization.
Preserving differential privacy in convolutional deep belief networks
TLDR
This work proposes the use of Chebyshev expansion to derive the approximate polynomial representation of objective functions of traditional CDBNs, and shows that the pCDBN is highly effective and significantly outperforms existing solutions.
...
1
2
3
4
5
...