Understanding the general properties of real social networks has gained much attention due to the proliferation of networked data. The nodes in the network are the individuals and the links among them denote their relationships. Many applications of networks such as anonymous Web browsing require relationship anonymity due to the sensitive, stigmatizing, or confidential nature of the relationship. One general approach for this problem is to randomize the edges in true networks, and only disclose the randomized networks. In this paper, we investigate how various properties of networks may be affected due to randomization. Specifically, we focus on the spectrum since the eigenvalues of a network are intimately connected to many important topological features. We also conduct theoretical analysis on the extent to which edge anonymity can be achieved. A spectrum preserving graph randomization method, which can better preserve network properties while protecting edge anonymity, is then presented and empirically evaluated.

Fairness-aware learning is increasingly important in data mining. Discrimination prevention aims to prevent discrimination in the training data before it is used to conduct predictive analysis. In this paper, we focus on fair data generation that ensures the generated data is discrimination free. Inspired by generative adversarial networks (GAN), we present fairness-aware generative adversarial networks, called FairGAN, which are able to learn a generator producing fair data and also preserving good data utility. Compared with the naive fair data generation models, FairGAN further ensures the classifiers which are trained on generated data can achieve fair classification on real data. Experiments on a real dataset show the effectiveness of FairGAN.

In this paper, we investigate the problem of discovering both direct and indirect discrimination from the historical data, and removing the discriminatory effects before the data is used for predictive analysis (e.g., building classifiers). The main drawback of existing methods is that they cannot distinguish the part of influence that is really caused by discrimination from all correlated influences. In our approach, we make use of the causal network to capture the causal structure of the data. Then we model direct and indirect discrimination as the path-specific effects, which accurately identify the two types of discrimination as the causal effects transmitted along different paths in the network. Based on that, we propose 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. Experiments using the real dataset show the effectiveness of our approaches.

In this paper, we focus on developing a novel mechanism to preserve differential privacy in deep neural networks, such that: (1) The privacy budget consumption is totally independent of the number of training steps; (2) It has the ability to adaptively inject noise into features based on the contribution of each to the output; and (3) It could be applied in a variety of different deep neural networks. To achieve this, we figure out a way to perturb affine transformations of neurons, and loss functions used in deep neural networks. In addition, our mechanism intentionally adds "more noise" into features which are "less relevant" to the model output, and vice-versa. Our theoretical analysis further derives the sensitivities and error bounds of our mechanism. Rigorous experiments conducted on MNIST and CIFAR-10 datasets show that our mechanism is highly effective and outperforms existing solutions.

Many online applications, such as online social networks or knowledge bases, are often attacked by malicious users who commit different types of actions such as vandalism on Wikipedia or fraudulent reviews on eBay. Currently, most of the fraud detection approaches require a training dataset that contains records of both benign and malicious users. However, in practice, there are often no or very few records of malicious users. In this paper, we develop one-class adversarial nets (OCAN) for fraud detection with only benign users as training data. OCAN first uses LSTM-Autoencoder to learn the representations of benign users from their sequences of online activities. It then detects malicious users by training a discriminator of a complementary GAN model that is different from the regular GAN model. Experimental results show that our 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.