Distributed Graph Neural Network (DGNN) is a powerful tool in large-scale graph representation learning. However, high data-transfer overhead among workers in a DGNN training job confines its scalability and thus the overall performance. Vertex-wise historical embedding methods have demonstrated high potential to alleviate the problems, but still suffer from severe accuracy loss and limited performance scalability, which has been attributed to the information loss of critical channels in historical vertices and redundant information in local channels. This article explores the optimization of channel level and construct a quantitative accuracy model for channel-wise historical embedding. We propose Sift, a novel DGNN training framework, supporting channel-wise partial historical embedding with accuracy guarantee. Sift has three components: a historical embedding evaluator with channel-wise quantitative accuracy model, a sawtooth-like matrix rearrangement for accelerating message passing, and a hybrid parallel framework for overlapping communication overhead. Comprehensive experimental results show that Sift achieves near-linear parallel convergence speedup, outperforming the state-of-the-art baselines by up to 72% in total training performance and up to 21% in convergence speed.

Social network data is widely shared, transferred and published for research purposes and business interests, but it has raised much concern on users' privacy. Even though users' identity information is always removed, attackers can still de-anonymize users with the help of auxiliary information. To protect against de-anonymization attack, various privacy protection techniques for social networks have been proposed. However, most existing approaches assume specific and restrict network structure as background knowledge and ignore semantic level prior belief of attackers, which are not always realistic in practice and do not apply to arbitrary privacy scenarios. Moreover, the privacy inference attack in the presence of semantic background knowledge is barely investigated. To address these shortcomings, in this work, we introduce knowledge graphs to explicitly express arbitrary prior belief of the attacker for any individual user. The processes of de-anonymization and privacy inference are accordingly formulated based on knowledge graphs. Our experiment on data of real social networks shows that knowledge graphs can power de-anonymization and inference attacks, and thus increase the risk of privacy disclosure. This suggests the validity of knowledge graphs as a general effective model of attackers' background knowledge for social network attack and privacy preservation.

In this paper, a set of accountable protocols denoted as AccountTrade is proposed for big data trading among dishonest consumers. For achieving a secure big data trading environment, AccountTrade achieves book-keeping ability and accountability against dishonest consumers throughout the trading (i.e., buying and selling) of datasets. We investigate the consumers' responsibilities in the dataset trading, then we design AccountTrade to achieve accountability against dishonest consumers that are likely to deviate from the responsibilities. Specifically, a uniqueness index is defined and proposed, which is a new rigorous measurement of the data uniqueness for this purpose. Furthermore, several accountable trading protocols are presented to enable data brokers to blame the misbehaving entities when misbehavior is detected. The accountability of AccountTrade is formally defined, proved, and evaluated by an automatic verification tool as well as extensive simulation with real-world datasets. Our evaluation shows that AccountTrade incurs at most 10-kB storage overhead per file, and it is capable of 8-1000 concurrent data upload requests per server.

Third-party analysis on private records is becoming increasingly important due to the widespread data collection for various analysis purposes. However, the data in its original form often contains sensitive information about individuals, and its publication will severely breach their privacy. In this paper, we present a novel Privacy-preserving Data Analytics framework PDA, which allows a third-party aggregator to obliviously conduct many different types of polynomial-based analysis on private data records provided by a dynamic sub-group of users. Notably, every user needs to keep only O(n) keys to join data analysis among O(2n) different groups of users, and any data analysis that is represented by polynomials is supported by our framework. Besides, a real implementation shows the performance of our framework is comparable to the peer works who present ad-hoc solutions for specific data analysis applications. Despite such nice properties of PDA, it is provably secure against a very powerful attacker (chosen-plaintext attack) even in the Dolev-Yao network model where all communication channels are insecure.

We propose AccountTrade, a set of accountable protocols, for big data trading among dishonest consumers. To secure the big data trading environment, our protocols achieve book-keeping ability and accountability against dishonest consumers who may misbehave throughout the dataset transactions. Specifically, we study the responsibilities of the consumers in the dataset trading and design AccountTrade to achieve accountability against the dishonest consumers who may try to deviate from their responsibilities. Specifically, we propose uniqueness index, a new rigorous measurement of the data uniqueness, as well as several accountable trading protocols to enable data brokers to blame the dishonest consumer when misbehavior is detected. We formally define, prove, and evaluate the accountability of our protocols by an automatic verification tool as well as extensive evaluation in real-world datasets. Our evaluation shows that AccountTrade incurs negligible constant storage overhead per file (<;10KB), and it is able to handle 8-1000 concurrent data uploading per server depending on the data types.

In this paper, we address a critical task of dynamically detecting the simultaneous behavior of driving and texting using smartphone as the sensor. We propose, design, and implement TEXIVE which achieves the goal of detecting texting operations during driving utilizing irregularities and rich micro-movements of users. Without relying on any external infrastructures and additional devices, and no need to bring any modification to vehicles, TEXIVE is able to successfully detect dangerous operations with good sensitivity, specificity, and accuracy by leveraging the inertial sensors integrated in regular smartphones. To validate our approach, we conduct extensive experiments involving in a number of volunteers on various of vehicles and smartphones. Our evaluation results show that TEXIVE has a classification accuracy of 87.18%, and precision of 96.67%.

Visible light communication (VLC) has been shown to have several advantages over traditional wireless communication. In this paper, we envision an LED-light-to-smartphone VLC protocol for delivering messages to a group of randomly arriving smartphone receivers. Our goal is to increase the throughput for large message delivery, as well as to reduce the delay of message broadcast. Key challenges for implementing such a VLC message broadcast protocol are: 1) the imperfect synchronization among receivers and the transmitter; 2) the receivers' arbitrary arrival times; and 3) the diversity of receivers' smartphones (e.g., location, capability, and frame-rates). In this paper, we propose a new modulation scheme and design link-layer protocols for improving the network data rate. We carefully design and implement our protocol, Martian, which allows smooth communication from the LED lights to a group of smartphone embedded cameras. Across several phone models, Martian can achieve data rate of about 1.6 kb/s even with NLOS -light. It also has a stable and small delay for broadcasting messages to the randomly arriving receivers.

Visible light communication (VLC) has been shown to have several advantages over traditional wireless communication. We envision a LED-to-smartphone VLC protocol for delivering messages to a group of unsynchronized mobile device receivers. We carefully design and implement our protocol, Martian, which allows smooth communication from the LED lights to a group of camera-enabled mobile devices. Across several phone models, Martian can achieve data rate of about 1.6kbps even with NLOS-light. Our intensive evaluations indicate that, the data rate reaches 4.2kbps on iPhone 6. This is a significant improvement compared with the 88bps data rate claimed by state-of-art design.

Aggregate statistics are becoming increasingly commonplace for mobile sensing applications which crowdsources data from individual users. In order to relieve user's concerns for privacy leakage, privacy preserving mechanisms have to be applied to enable the aggregator to compute aggregate statistics without learning each individual data. Although the aggregator will not know the value of the data, it is necessary to ensure the (semantic) validity of the data contributed by users. In this work, we design a privacy-preserving protocol for an aggregator to compute corrected aggregated statistics over users' data that can both preserve user's privacy and verify the semantic validity of the data. We evaluated our protocol on real-world dataset and demonstrated the efficiency of our protocol.

With the increased popularity of smartphones, various security threats and privacy leakages targeting them are discovered and investigated. In this work, we present SilentSense, a framework to authenticate users silently and transparently by exploiting dynamics mined from the user touch behavior biometrics and the micro-movement of the device caused by user's screen-touch actions. We build a “touch-based biometrics” model of the owner by extracting some principle features, and then verify whether the current user is the owner or guest/attacker. When using the smartphone, some unique operating dynamics of the user is detected and learnt by collecting the sensor data and touch events silently. When users are mobile, the micro-movement of mobile devices caused by touch is suppressed by that due to the large scale user-movement which will render the touch-based biometrics ineffective. To address this, we integrate a movement-based biometrics for each user with previous touch-based biometrics. We conduct extensive evaluations of our approaches on the Android smartphone, we show that the user identification accuracy is over 99%.

For mobile devices, communication via cellular networks consumes more energy than via WiFi networks, and suffers an expensive limited data plan. On the other hand, as the coverage and the density of WiFI networks are smaller than those of the cellular networks, users cannot purely rely on WiFi to access the Internet. In this work we present a behavior-aware and preference-based approach to prefetch news webpages for the user to visit in the near future, by exploiting the WiFi network connections to reduce the energy and monetary cost. We first design an efficient preference learning algorithm to keep track of the user's changing interests, and then by predicting the appearance and durations of the WiFi network connections, our prefetch approach optimizes when to prefetch to maximize the user experience while lowing the prefetch cost. Our prefetch approach also exploits the idle period of WiFi connections to reduce the tail-energy consumption. We implement our approach in iPhone and our extensive evaluations show that our system achieves about 60% hit ratio, saves about 50% cellular data usage, and reduces the energy cost by 7%.

Legacy 802.11b/g protocols have been successfully applied in wireless long-distance (WiLD) networks to provide low-cost network connectivity for rural areas and developing countries, by designing TDMA MAC protocols. In contrast, we investigate the performance, and enhancement of using 802.11n for WiLD networks still using CSMA/CA. Our extensive experiments from our testbed show that, although 802.11n with CSMA/CA can provide network connectivity in WiLD environment, it suffers from poor performance. We thus propose RainbowRate, an efficient rate adaptation mechanism specified for WiLD links. RainbowRate leverages unique features found in WiLD links. We implement RainbowRate in off-the-shelf platforms and evaluate various aspects of our design using a testbed consisting of 6 mesh routers and 7 long-distance links, with the longest link length 20 km. Our experiment results show that RainbowRate out-performs state-of-the-art RA algorithms (MiRA, Ath9k and Minstrel) significantly in terms of throughput.

Effective and energy efficient neighbor discovery protocol is a crucial component for the success of emerging opportunistic encounter-based mobile (ad hoc) networking for social and gaming. In this work, we design P-Game, an effective neighbor discovery protocol to find a group of neighbors. By leveraging a quick estimation of the number of neighbors, we design various protocols for collecting the IDs of these neighboring nodes with the objective of either minimizing the latency of neighbor-discovery process or minimizing the active slots (i.e. energy consumption) of each neighbor. We validate PickupGame through rigorous theoretical analysis. When the required acquaintances k is a constant fraction of neighbors, our protocol is proved to have optimum delay T(k) and optimum active slots T(1). When we need to find all neighbors, our protocols achieve tradeoffs in the delay and active slots: one approach has discovery latency O(k ln ln k) and active slots O(ln ln k). Our evaluations corroborate our theoretical results and show considerable improvement in discovery latency over existing approaches in almost all cases.

GasNet is a sensor network for real-timely monitoring the gas leak in residential buildings, in order to efficiently protect the buildings from gas leak explosion. GasNet provides low-latency and reliable gas leak ALARM message delivery in complicated RF environments. It does so through ROAP, a novel opportunistic forwarding mechanism considering link correlation. ROAP leverages a hop tree in opportunistic forwarder list selection to ensure the shortest hops to the sink. Furthermore, link correlation is used to obtain more accurate forwarding probability and to achieve fast retransmission. We implement the prototype of GasNet in campus testbed and evaluate its performance via extensive experiments. The experiment results show that ROAP achieves 100% gas leak ALARM message delivery in low latency.

We study the multicast capacity of a random wireless network consisting of n randomly placed ordinary wireless nodes and m regularly placed base stations in a square region, known as a hybrid network. All ordinary wireless nodes have the uniform transmission range r and uniform interference range R=θ(r) and they can transmit/receive at Wa-bps. Each base station can communicate with adjacent base stations directly with a data rate WB-bps and the data transmission rate between a base station and a wireless node is assumed to be Wc-bps. Assume that there is a random set of ns ordinary wireless nodes that will serve as the source nodes of ns multicast flows (each has randomly selected k-1 receivers). Each flow will have data rate λi bps. We found that the minimum per-flow multicast capacity min n s over i = 1 λi for hybrid networks has three regimes, and for each regime we derive matching asymptotic upper and lower bounds. Thus it closes the gap of previous results in the literature.