Federated learning (FL) is a framework for collaborative learning among users through a coordinating server. A recent HyperNetwork-based personalized FL framework, called HyperNetFL, is used to generate local models using personalized descriptors optimized for each user independently. However, HyperNetFL introduces unknown privacy risks. This paper introduces a novel approach to preserve user-level differential privacy, dubbed User-level DP, by providing formal privacy protection for data owners in training a HyperNetFL model. To achieve that, our proposed algorithm, called UDP-Alg, optimizes the trade-off between privacy loss and model utility by tightening sensitivity bounds. An intensive evaluation using benchmark datasets shows that our proposed UDP-Alg significantly improves privacy protection at a modest cost in utility.

In this paper, we introduce a novel concept of user-entity differential privacy (UeDP) to provide formal privacy protection simultaneously to both sensitive entities in textual data and data owners in learning natural language models (NLMs). To preserve UeDP, we developed a novel algorithm, called UeDP-Alg, optimizing the trade-off between privacy loss and model utility with a tight sensitivity bound derived from seamlessly combining user and sensitive entity sampling processes. An extensive theoretical analysis and evaluation show that our UeDP-Alg outperforms baseline approaches in model utility under the same privacy budget consumption on several NLM tasks, using benchmark datasets.

Graph neural networks (GNNs) are susceptible to privacy inference attacks (PIAS) given their ability to learn joint representation from features and edges among nodes in graph data. To prevent privacy leakages in GNNs, we propose a novel heterogeneous randomized response (HeteroRR) mechanism to protect nodes’ features and edges against PIAS under differential privacy (DP) guarantees, without an undue cost of data and model utility in training GNNs. Our idea is to balance the importance and sensitivity of nodes’ features and edges in redistributing the privacy budgets since some features and edges are more sensitive or important to the model utility than others. As a result, we derive significantly better randomization probabilities and tighter error bounds at both levels of nodes’ features and edges departing from existing approaches, thus enabling us to maintain high data utility for training GNNs. An extensive theoretical and empirical analysis using benchmark datasets shows that HeteroRR significantly outperforms various baselines in terms of model utility under rigorous privacy protection for both nodes’ features and edges. That enables us to defend PIAs in DP-preserving GNNs effectively.

The pervasiveness of neural networks (NNs) in critical computer vision and image processing applications makes them very attractive for adversarial manipulation. A large body of existing research thoroughly investigates two broad categories of attacks targeting the integrity of NN models. The first category of attacks, commonly called Adversarial Examples, perturbs the model’s inference by carefully adding noise into input examples. In the second category of attacks, adversaries try to manipulate the model during the training process by implanting Trojan backdoors. Researchers show that such attacks pose severe threats to the growing applications of NNs and propose several defenses against each attack type individually. However, such one-sided defense approaches leave potentially unknown risks in real-world scenarios when an adversary can unify different attacks to create new and more lethal ones bypassing existing defenses.In this work, we show how to jointly exploit adversarial perturbation and model poisoning vulnerabilities to practically launch a new stealthy attack, dubbed AdvTrojan. AdvTrojan is stealthy because it can be activated only when: 1) a carefully crafted adversarial perturbation is injected into the input examples during inference, and 2) a Trojan backdoor is implanted during the training process of the model. We leverage adversarial noise in the input space to move Trojan-infected examples across the model decision boundary, making it difficult to detect. The stealthiness behavior of AdvTrojan fools the users into accidentally trusting the infected model as a robust classifier against adversarial examples. AdvTrojan can be implemented by only poisoning the training data similar to conventional Trojan backdoor attacks. Our thorough analysis and extensive experiments on several benchmark datasets show that AdvTrojan can bypass existing defenses with a success rate close to 100% in most of our experimental scenarios and can be extended to attack federated learning as well as high-resolution images.

In many image-classification applications, understanding the reasons of model’s prediction can be as critical as the prediction’s accuracy itself. Various feature-based local explainers have been designed to provide explanations on the decision of complex classifiers. Nevertheless, there is no consensus on evaluating the quality of different explanations. In response to this lack of comprehensive evaluation, we introduce the c-Eval metric and its corresponding framework to quantify the feature-based local explanation’s quality. Given a classifier’s prediction and the corresponding explanation on that prediction, c-Eval is the minimum-distortion perturbation that successfully alters the prediction while keeping the explanation’s features unchanged. To show that c-Eval captures the importance of input’s features, we establish a connection between c-Eval and the features returned by explainers in affine and nearly-affine classifiers. We then introduce the c-Eval plot, which not only displays a strong connection between c-Eval and explainers’ quality, but also helps automatically determine explainer’s parameters.

In this paper, we present a community-focused drug abuse monitoring and supporting system, called DrugTracker, that utilizes social media and geospatial data in near real-time. Through the system, users can: (1) Detect drug abuse risk behaviors from social media platforms, e.g., Twitter; (2) Analyze drug abuse risk behaviors by querying consolidated and live datasets with keywords, spatial entities, and time constraints; and (3) Explore the query results and associated data through a web-based user interface in thematic choropleth, heatmap, and statistical charts. To protect the privacy of the Twitter users, whose data is collected, the system automatically hides the re-identification elements in tweets and aggregates the geo-tags into areas such as census tracts. For the demonstration purpose, our DrugTracker system is populated with a database that contains about 10 million tweets from the year 2017, that were annotated as drug abuse risk behavior positive by our deep learning model.

The success of question and answer (Q&A) websites attracts massive user-generated content for using and learning APIs, which easily leads to information overload: many questions for APIs have a large number of answers containing useful and irrelevant information, and cannot all be consumed by developers. In this work, we develop DeepTip, a novel deep learning-based approach using different Convolutional Neural Network architectures, to extract short practical and useful tips from developer answers. Our extensive empirical experiments prove that DeepTip can extract useful tips from a large corpus of answers to questions with high precision (i.e., avg. 0.854) and coverage (i.e., 0.94), and it outperforms two state-of-the-art baselines by up to 56.7% and 162%, respectively, in terms of Precision. Furthermore, qualitatively, a user study is conducted with real Stack Overflow users and its results confirm that tip extraction is useful and our approach generates high-quality tips.

Prescription drug abuse is one of the fastest growing public health problems in the USA. To address this epidemic, a near real-time monitoring strategy, instead of one resorting to a retrospective health records, may improve detecting the prevalence and patterns of abuse of both illegal drugs and prescription medications. In this paper, our primary goals are to demonstrate the possibility of utilizing social media, e.g., Twitter, for automatic monitoring of illegal drug and prescription medication abuse. We use machine learning methods for an automatic classification that can identify tweets that are indicative of drug abuse. We collected tweets associated with well-known illegal and prescription drugs. We manually annotated 300 tweets that are likely to be related to drug abuse. Our experiment compares a set of classification algorithms, and a decision tree classifier J48, and the SVM outperform others for determining whether tweets contain signals of drug abuse. This automatic supervised classification study results illustrate the utility of Twitter in examining patterns of abuse, and show the feasibility of building the drug abuse detection system that can process large volume data from social media sources in a near real-time.

The blooming availability of traces for social, biological, and communication networks opens up unprecedented opportunities in analyzing diffusion processes in networks. However, the sheer sizes of the nowadays networks raise serious challenges in computational efficiency and scalability. In this paper, we propose a new hyper-graph sketching framework for influence dynamics in networks. The core of our sketching framework, called SKIS, is an efficient importance sampling algorithm that returns only non-singular reverse cascades in the network. Comparing to previously developed sketches like RIS and SKIM, our sketch significantly enhances estimation quality while substantially reducing processing time and memory-footprint. Further, we present general strategies of using SKIS to enhance existing algorithms for influence estimation and influence maximization which are motivated by practical applications like viral marketing. Using SKIS, wedesign high-quality influence oracles for seed sets with average estimation error up to 10x times smaller than those using RIS and 6x times smaller than SKIMs. In addition, our influence maximization using SKIS substantially improves the quality of solutions for greedy algorithms. It achieves up to 10x times speed-up and 4x memory reduction for the fastest RIS-based DSSA algorithm, while maintaining the same theoretical guarantees.

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.

Modeling physical activity propagation, such as activity level and intensity, is a key to preventing obesity from cascading through communities, and to helping spread wellness and healthy behavior in a social network. However, there have not been enough scientific and quantitative studies to elucidate how social communication may deliver physical activity interventions. In this work, we introduce a novel model named T opic-aware C ommunity-level P hysical Activity Propagation with T emporal Dynamics (TCPT) to analyze physical activity propagation and social influence at different granularities (i.e., individual level and community level). Given a social network, the TCPT model first integrates the correlations between the content of social communication, social influences, and temporal dynamics. Then, a hierarchical approach is utilized to detect a set of communities and their reciprocal influence strength of physical activities. The experimental evaluation shows not only the effectiveness of our approach but also the correlation of the detected communities with various health outcome measures. Our promising results pave a way for knowledge discovery in health social networks.

Modeling and predicting human behaviors, such as the activity level and intensity, is the key to prevent the cascades of obesity, and help spread wellness and healthy behavior in a social network. The user diversity, dynamic behaviors, and hidden social influences make the problem more challenging. In this work, we propose a deep learning model named Social Restricted Boltzmann Machine (SRBM) for human behavior modeling and prediction in health social networks. In the proposed SRBM model, we naturally incorporate self-motivation, implicit and explicit social influences, and environmental events together into three layers which are historical, visible, and hidden layers. The interactions among these behavior determinants are naturally simulated through parameters connecting these layers together. The contrastive divergence and back-propagation algorithms are employed for training the model. A comprehensive experiment on real and synthetic data has shown the great effectiveness of our deep learning model compared with conventional methods.

Gradual patterns highlight covariations of attributes of the form “The more/less X, the more/less Y”. Their usefulness in several applications has recently stimulated the synthesis of several algorithms for their automated discovery from large datasets. However, existing techniques require all the interesting data to be in a single database relation or table. This paper extends the notion of gradual pattern to the case in which the co-variations are possibly expressed between attributes of different database relations. The interestingness measure for this class of “relational gradual patterns” is defined on the basis of both Kendall's τ and gradual supports. Moreover, this paper proposes two algorithms, named τRGP Miner and gRGP Miner, for the discovery of relational gradual rules. Three pruning strategies to reduce the search space are proposed. The efficiency of the algorithms is empirically validated, and the usefulness of relational gradual patterns is proved on some real-world databases.

Modeling physical activity propagation, such as the activity level and intensity, is the key to prevent the cascades of obesity, and help spread wellness and healthy behavior in a social network. However, there has been lacking of scientific and quantitative study to elucidate how social communication may deliver physical activity interventions. In this work we introduce a Community-level Physical Activity Propagation (CPP) model to analyze physical activity propagation and social influence at different granularities (i.e., individual level and community level). CPP is a novel model which is inspired by the well-known Independent Cascade and Community-level Social Influence models. Given a social network, we utilize a hierarchical approach to detect a set of communities and their reciprocal influence strength of physical activities. CPP provides a powerful tool to discover, summarize, and investigate influence patterns of physical activities in a health social network. The detail experimental evaluation shows not only the effectiveness of our approach but also the correlation of the detected communities with various health outcome measures (i.e., both existing ones and our novel measure, named Wellness score, which is a combination of lifestyle parameters, biometrics, and biomarkers). Our promising results potentially pave a way for knowledge discovery in health social networks.

One of the objectives of spatio-temporal data mining is to analyze moving object datasets to exploit interesting patterns. Traditionally, existing methods only focus on an unchanged group of moving objects during a time period. Thus, they cannot capture object moving trends which can be very useful for better understanding the natural moving behavior in various real world applications. In this paper, we present a novel concept of "time relaxed gradual trajectory pattern", denoted real-Gpattern, which captures the object movement tendency. Additionally, we also propose an efficient algorithm, called ClusterGrowth, designed to extract the complete set of all interesting maximal real-Gpatterns. Conducted experiments on real and large synthetic datasets demonstrate the effectiveness, parameter sensitiveness and efficiency of our methods.

Most clustering algorithms tend to separate large scale online communities into several meaningful sub-communities by extracting cut points and cut edges. However, these algorithms are not effective on dense and concentrated graphs which do not have any meaningful cut points. Common problems with the previous algorithms are as follows. First, the size of the first cluster is too large as it may contain many incompatible users. Second, the quality and the purity of the clusters are very low. Third, only the dominant first cluster is found to be meaningful. To address these problems, we first propose a graph transformation to separate large scale online communities into two different types of meaningful subgraphs. The first subgraph is the intimacy graph and the second is the reputation graph. Then, we present the effective algorithms for discovering good sub-communities and for excluding incompatible users in these subgraphs. The experimental results show that our algorithms allow for extracting more suitable and meaningful sub-communities than the previous work in dense online networks.