Deep learning techniques based on neural networks have shown significant success in a wide range of AI tasks. Large-scale training datasets are one of the critical factors for their success. However, when the training datasets are crowdsourced from individuals and contain sensitive information, the model parameters may encode private information and bear the risks of privacy leakage. The recent growing trend of the sharing and publishing of pre-trained models further aggravates such privacy risks. To tackle this problem, we propose a differentially private approach for training neural networks. Our approach includes several new techniques for optimizing both privacy loss and model accuracy. We employ a generalization of differential privacy called concentrated differential privacy(CDP), with both a formal and refined privacy loss analysis on two different data batching methods. We implement a dynamic privacy budget allocator over the course of training to improve model accuracy. Extensive experiments demonstrate that our approach effectively improves privacy loss accounting, training efficiency and model quality under a given privacy budget.

Abstract-This paper introduces concepts and algorithms of feature selection, surveys existing feature selection algorithms for classification and clustering, groups and compares different algorithms with a categorizing framework based on search strategies, evaluation criteria, and data mining tasks, reveals unattempted combinations, and provides guidelines in selecting feature selection algorithms. With the categorizing framework, we continue our efforts toward building an integrated system for intelligent feature selection. A unifying platform is proposed as an intermediate step. An illustrative example is presented to show how existing feature selection algorithms can be integrated into a meta algorithm that can take advantage of individual algorithms. An added advantage of doing so is to help a user employ a suitable algorithm without knowing details of each algorithm. Some real-world applications are included to demonstrate the use of feature selection in data mining. We conclude this work by identifying trends and challenges of feature selection research and development.

Membership inference attacks seek to infer membership of individual training instances of a model to which an adversary has black-box access through a machine learning-as-a-service API. In providing an in-depth characterization of membership privacy risks against machine learning models, this paper presents a comprehensive study towards demystifying membership inference attacks from two complimentary perspectives. First, we provide a generalized formulation of the development of a black-box membership inference attack model. Second, we characterize the importance of model choice on model vulnerability through a systematic evaluation of a variety of machine learning models and model combinations using multiple datasets. Through formal analysis and empirical evidence from extensive experimentation, we characterize under what conditions a model may be vulnerable to such black-box membership inference attacks. We show that membership inference vulnerability is data-driven and corresponding attack models are largely transferable. Though different model types display different vulnerabilities to membership inference, so do different datasets. Our empirical results additionally show that (1) using the type of target model under attack within the attack model may not increase attack effectiveness and (2) collaborative learning exposes vulnerabilities to membership inference risks when the adversary is a participant. We also discuss countermeasure and mitigation strategies.

Many feature selection algorithms have been proposed in the past focusing on improving classification accuracy. In this work, we point out the importance of stable feature selection for knowledge discovery from high-dimensional data, and identify two causes of instability of feature selection algorithms: selection of a minimum subset without redundant features and small sample size. We propose a general framework for stable feature selection which emphasizes both good generalization and stability of feature selection results. The framework identifies dense feature groups based on kernel density estimation and treats features in each dense group as a coherent entity for feature selection. An efficient algorithm DRAGS (Dense Relevant Attribute Group Selector) is developed under this framework. We also introduce a general measure for assessing the stability of feature selection algorithms. Our empirical study based on microarray data verifies that dense feature groups remain stable under random sample hold out, and the DRAGS algorithm is effective in identifying a set of feature groups which exhibit both high classification accuracy and stability.

In gene expression microarray data analysis, selecting a small number of discriminative genes from thousands of genes is an important problem for accurate classification of diseases or phenotypes. The problem becomes particularly challenging due to the large number of features (genes) and small sample size. Traditional gene selection methods often select the top-ranked genes according to their individual discriminative power without handling the high degree of redundancy among the genes. Latest research shows that removing redundant genes among selected ones can achieve a better representation of the characteristics of the targeted phenotypes and lead to improved classification accuracy. Hence, we study in this paper the relationship between feature relevance and redundancy and propose an efficient method that can effectively remove redundant genes. The efficiency and effectiveness of our method in comparison with representative methods has been demonstrated through an empirical study using public microarray data sets.