arXiv subjects

Xiang-Yang Li

Publications and source records attributed to Xiang-Yang Li.

At least 73 records · Page 4Linked to original sources

arXiv2019

Unsupervised Pivot Translation for Distant Languages

Unsupervised neural machine translation (NMT) has attracted a lot of attention recently. While state-of-the-art methods for unsupervised translation usually perform well between similar languages (e.g., English-German translation), they perform poorly between distant languages, because unsupervised alignment does not work well for distant languages. In this work, we introduce unsupervised pivot translation for distant languages, which translates a language to a distant language through multiple hops, and the unsupervised translation on each hop is relatively easier than the original direct translation. We propose a learning to route (LTR) method to choose the translation path between the source and target languages. LTR is trained on language pairs whose best translation path is available and is applied on the unseen language pairs for path selection. Experiments on 20 languages and 294 distant language pairs demonstrate the advantages of the unsupervised pivot translation for distant languages, as well as the effectiveness of the proposed LTR for path selection. Specifically, in the best case, LTR achieves an improvement of 5.58 BLEU points over the conventional direct unsupervised method.

cs.CL↗

arXiv2018

From Communication to Sensing : Recognizing and Counting Repetitive Motions with Wireless Backscattering

Recently several ground-breaking RF-based motion recognition systems were proposed to detect and/or recognize macro/micro human movements. These systems often suffer from various interferences caused by multiple-users moving simultaneously, resulting in extremely low recognition accuracy. To tackle this challenge, we propose a novel system, called Motion-Fi, which marries battery free wireless backscattering and device-free sensing. Motion-Fi is an accurate, interference tolerable motion-recognition system, which counts repetitive motions without using scenario-dependent templates or profiles and enables multi-users performing certain motions simultaneously because of the relatively short transmission range of backscattered signals. Although the repetitive motions are fairly well detectable through the backscattering signals in theory, in reality they get blended into various other system noises during the motion. Moreover, irregular motion patterns among users will lead to expensive computation cost for motion recognition. We build a backscattering wireless platform to validate our design in various scenarios for over 6 months when different persons, distances and orientations are incorporated. In our experiments, the periodicity in motions could be recognized without any learning or training process, and the accuracy of counting such motions can be achieved within 5% count error. With little efforts in learning the patterns, our method could achieve 93.1% motion-recognition accuracy for a variety of motions. Moreover, by leveraging the periodicity of motions, the recognition accuracy could be further improved to nearly 100% with only 3 repetitions. Our experiments also show that the motions of multiple persons separating by around 2 meters cause little accuracy reduction in the counting process.

eess.SP↗

arXiv2018

Learning to Teach

Teaching plays a very important role in our society, by spreading human knowledge and educating our next generations. A good teacher will select appropriate teaching materials, impact suitable methodologies, and set up targeted examinations, according to the learning behaviors of the students. In the field of artificial intelligence, however, one has not fully explored the role of teaching, and pays most attention to machine \emph{learning}. In this paper, we argue that equal attention, if not more, should be paid to teaching, and furthermore, an optimization framework (instead of heuristics) should be used to obtain good teaching strategies. We call this approach `learning to teach'. In the approach, two intelligent agents interact with each other: a student model (which corresponds to the learner in traditional machine learning algorithms), and a teacher model (which determines the appropriate data, loss function, and hypothesis space to facilitate the training of the student model). The teacher model leverages the feedback from the student model to optimize its own teaching strategies by means of reinforcement learning, so as to achieve teacher-student co-evolution. To demonstrate the practical value of our proposed approach, we take the training of deep neural networks (DNN) as an example, and show that by using the learning to teach techniques, we are able to use much less training data and fewer iterations to achieve almost the same accuracy for different kinds of DNN models (e.g., multi-layer perceptron, convolutional neural networks and recurrent neural networks) under various machine learning tasks (e.g., image classification and text understanding).

cs.LG↗

arXiv2017

VoiceMask: Anonymize and Sanitize Voice Input on Mobile Devices

Voice input has been tremendously improving the user experience of mobile devices by freeing our hands from typing on the small screen. Speech recognition is the key technology that powers voice input, and it is usually outsourced to the cloud for the best performance. However, the cloud might compromise users' privacy by identifying their identities by voice, learning their sensitive input content via speech recognition, and then profiling the mobile users based on the content. In this paper, we design an intermediate between users and the cloud, named VoiceMask, to sanitize users' voice data before sending it to the cloud for speech recognition. We analyze the potential privacy risks and aim to protect users' identities and sensitive input content from being disclosed to the cloud. VoiceMask adopts a carefully designed voice conversion mechanism that is resistant to several attacks. Meanwhile, it utilizes an evolution-based keyword substitution technique to sanitize the voice input content. The two sanitization phases are all performed in the resource-limited mobile device while still maintaining the usability and accuracy of the cloud-supported speech recognition service. We implement the voice sanitizer on Android systems and present extensive experimental results that validate the effectiveness and efficiency of our app. It is demonstrated that we are able to reduce the chance of a user's voice being identified from 50 people by 84% while keeping the drop of speech recognition accuracy within 14.2%.

cs.CR↗

arXiv2017

Social Network De-anonymization: More Adversarial Knowledge, More Users Re-Identified?

Following the trend of data trading and data publishing, many online social networks have enabled potentially sensitive data to be exchanged or shared on the web. As a result, users' privacy could be exposed to malicious third parties since they are extremely vulnerable to de-anonymization attacks, i.e., the attacker links the anonymous nodes in the social network to their real identities with the help of background knowledge. Previous work in social network de-anonymization mostly focuses on designing accurate and efficient de-anonymization methods. We study this topic from a different perspective and attempt to investigate the intrinsic relation between the attacker's knowledge and the expected de-anonymization gain. One common intuition is that the more auxiliary information the attacker has, the more accurate de-anonymization becomes. However, their relation is much more sophisticated than that. To simplify the problem, we attempt to quantify background knowledge and de-anonymization gain under several assumptions. Our theoretical analysis and simulations on synthetic and real network data show that more background knowledge may not necessarily lead to more de-anonymization gain in certain cases. Though our analysis is based on a few assumptions, the findings still leave intriguing implications for the attacker to make better use of the background knowledge when performing de-anonymization, and for the data owners to better measure the privacy risk when releasing their data to third parties.

cs.SI↗

arXiv2017

Opportunistic Forwarding with Partial Centrality

In opportunistic networks, the use of social metrics (e.g., degree, closeness and betweenness centrality) of human mobility network, has recently been shown to be an effective solution to improve the performance of opportunistic forwarding algorithms. Most of the current social-based forwarding schemes exploit some globally defined node centrality, resulting in a bias towards the most popular nodes. However, these nodes may not be appropriate relay candidates for some target nodes, because they may have low importance relative to these subsets of target nodes. In this paper, to improve the opportunistic forwarding efficiency, we exploit the relative importance (called partial centrality) of a node with respect to a group of nodes. We design a new opportunistic forwarding scheme, opportunistic forwarding with partial centrality (OFPC), and theoretically quantify the influence of the partial centrality on the data forwarding performance using graph spectrum. By applying our scheme on three real opportunistic networking scenarios, our extensive evaluations show that our scheme achieves significantly better mean delivery delay and cost compared to the state-of-the-art works, while achieving delivery ratios sufficiently close to those by Epidemic under different TTL requirements.

cs.NI↗

arXiv2016

Mutual Information Optimally Local Private Discrete Distribution Estimation

Consider statistical learning (e.g. discrete distribution estimation) with local $ε$-differential privacy, which preserves each data provider's privacy locally, we aim to optimize statistical data utility under the privacy constraints. Specifically, we study maximizing mutual information between a provider's data and its private view, and give the exact mutual information bound along with an attainable mechanism: $k$-subset mechanism as results. The mutual information optimal mechanism randomly outputs a size $k$ subset of the original data domain with delicate probability assignment, where $k$ varies with the privacy level $ε$ and the data domain size $d$. After analysing the limitations of existing local private mechanisms from mutual information perspective, we propose an efficient implementation of the $k$-subset mechanism for discrete distribution estimation, and show its optimality guarantees over existing approaches.

cs.IT↗

arXiv2016

Estimation of Passenger Route Choice Pattern Using Smart Card Data for Complex Metro Systems

Nowadays, metro systems play an important role in meeting the urban transportation demand in large cities. The understanding of passenger route choice is critical for public transit management. The wide deployment of Automated Fare Collection(AFC) systems opens up a new opportunity. However, only each trip's tap-in and tap-out timestamp and stations can be directly obtained from AFC system records; the train and route chosen by a passenger are unknown, which are necessary to solve our problem. While existing methods work well in some specific situations, they don't work for complicated situations. In this paper, we propose a solution that needs no additional equipment or human involvement than the AFC systems. We develop a probabilistic model that can estimate from empirical analysis how the passenger flows are dispatched to different routes and trains. We validate our approach using a large scale data set collected from the Shenzhen metro system. The measured results provide us with useful inputs when building the passenger path choice model.

cs.AI↗

arXiv2015

PDA: Semantically Secure Time-Series Data Analytics with Dynamic Subgroups

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(2^n) 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.

cs.CR↗

arXiv2015

WalkieLokie: Relative Positioning for Augmented Reality Using a Dummy Acoustic Speaker

We propose and implement a novel relative positioning system, WalkieLokie, to enable more kinds of Augmented Reality applications, e.g., virtual shopping guide, virtual business card sharing. WalkieLokie calculates the distance and direction between an inquiring user and the corresponding target. It only requires a dummy speaker binding to the target and broadcasting inaudible acoustic signals. Then the user walking around can obtain the position using a smart device. The key insight is that when a user walks, the distance between the smart device and the speaker changes; and the pattern of displacement (variance of distance) corresponds to the relative position. We use a second-order phase locked loop to track the displacement and further estimate the position. To enhance the accuracy and robustness of our strategy, we propose a synchronization mechanism to synthesize all estimation results from different timeslots. We show that the mean error of ranging and direction estimation is 0.63m and 2.46 degrees respectively, which is accurate even in case of virtual business card sharing. Furthermore, in the shopping mall where the environment is quite severe, we still achieve high accuracy of positioning one dummy speaker, and the mean position error is 1.28m.

cs.CY↗

arXiv2015

A Visible Light Based Indoor Positioning System

In this paper, we propose a novel indoor localization scheme that exploits ubiquitous visible lights, which are necessarily and densely deployed in almost all indoor environments. We unveil two phenomena of lights available for positioning: 1) the light strength varies according to different light sources, which can be easily detected by light sensors embedded in COTS devices (e.g., smart-phone, smart-glass and smart-watch); 2) the light strength is stable in different times of the day thus exploiting it can avoid frequent site-survey and database maintenance. Hence, a user could locate oneself by differentiating the light source of received light strength (RLS). However, different from existing positioning systems that exploit special LEDs, ubiquitous visible lights lack fingerprints that can uniquely identify the light source, which results in an ambiguity problem that an RLS may correspond to multiple positions. Moreover, RLS is not only determined by device's position, but also seriously affected by its orientation, which causes great complexity in site-survey. To address these challenges, we first propose and validate a realistic light strength model that can attributes RLS to arbitrary positions with heterogenous orientations. This model is further perfected by taking account of the device diversity, influence of multiple light sources and shading of obstacles. Then we design a localizing scheme that harness user's mobility to generate spatial-related RLS to tackle the position-ambiguity problem of a single RLS, which is robust against sunlight interference, shading effect of human-body and unpredictable behaviours (e.g., put the device in pocket) of user. Experiment results show that our scheme achieves mean accuracy $1.93$m and $1.98$m in office ($720m^2$) and library scenario ($960m^2$) respectively.

cs.NI↗

arXiv2015

General Capacity for Deterministic Dissemination in Wireless Ad Hoc Networks

In this paper, we study capacity scaling laws of the deterministic dissemination (DD) in random wireless networks under the generalized physical model (GphyM). This is truly not a new topic. Our motivation to readdress this issue is two-fold: Firstly, we aim to propose a more general result to unify the network capacity for general homogeneous random models by investigating the impacts of different parameters of the system on the network capacity. Secondly, we target to close the open gaps between the upper and the lower bounds on the network capacity in the literature. The generality of this work lies in three aspects: (1) We study the homogeneous random network of a general node density $λ\in [1,n]$, rather than either random dense network (RDN, $λ=n$) or random extended network (REN, $λ=1$) as in the literature. (2) We address the general deterministic dissemination sessions, \ie, the general multicast sessions, which unify the capacities for unicast and broadcast sessions by setting the number of destinations for each session as a general value $n_d\in[1,n]$. (3) We allow the number of sessions to change in the range $n_s\in(1,n]$, instead of assuming that $n_s=Θ(n)$ as in the literature. We derive the general upper bounds on the capacity for the arbitrary case of $(λ, n_d, n_s)$ by introducing the Poisson Boolean model of continuum percolation, and prove that they are tight according to the existing general lower bounds constructed in the literature.

cs.IT↗

arXiv2015

Enabling Privacy-preserving Auctions in Big Data

We study how to enable auctions in the big data context to solve many upcoming data-based decision problems in the near future. We consider the characteristics of the big data including, but not limited to, velocity, volume, variety, and veracity, and we believe any auction mechanism design in the future should take the following factors into consideration: 1) generality (variety); 2) efficiency and scalability (velocity and volume); 3) truthfulness and verifiability (veracity). In this paper, we propose a privacy-preserving construction for auction mechanism design in the big data, which prevents adversaries from learning unnecessary information except those implied in the valid output of the auction. More specifically, we considered one of the most general form of the auction (to deal with the variety), and greatly improved the the efficiency and scalability by approximating the NP-hard problems and avoiding the design based on garbled circuits (to deal with velocity and volume), and finally prevented stakeholders from lying to each other for their own benefit (to deal with the veracity). We achieve these by introducing a novel privacy-preserving winner determination algorithm and a novel payment mechanism. Additionally, we further employ a blind signature scheme as a building block to let bidders verify the authenticity of their payment reported by the auctioneer. The comparison with peer work shows that we improve the asymptotic performance of peer works' overhead from the exponential growth to a linear growth and from linear growth to a logarithmic growth, which greatly improves the scalability.

cs.CR↗

arXiv2014

Enable Portrait Privacy Protection in Photo Capturing and Sharing

The wide adoption of wearable smart devices with onboard cameras greatly increases people's concern on privacy infringement. Here we explore the possibility of easing persons from photos captured by smart devices according to their privacy protection requirements. To make this work, we need to address two challenges: 1) how to let users explicitly express their privacy protection intention, and 2) how to associate the privacy requirements with persons in captured photos accurately and efficiently. Furthermore, the association process itself should not cause portrait information leakage and should be accomplished in a privacy-preserving way. In this work, we design, develop, and evaluate a protocol, that enables a user to flexibly express her privacy requirement and empowers the photo service provider (or image taker) to exert the privacy protection policy.Leveraging the visual distinguishability of people in the field-of-view and the dimension-order-independent property of vector similarity measurement, we achieves high accuracy and low overhead. We implement a prototype system, and our evaluation results on both the trace-driven and real-life experiments confirm the feasibility and efficiency of our system.

cs.CR↗

arXiv2014

Outsource Photo Sharing and Searching for Mobile Devices With Privacy Protection

With the proliferation of mobile devices, cloud-based photo sharing and searching services are becoming common due to the mobile devices' resource constrains. Meanwhile, there is also increasing concern about privacy in photos. In this work, we present a framework \ourprotocolNSP, which enables cloud servers to provide privacy-preserving photo sharing and search as a service to mobile device users. Privacy-seeking users can share their photos via our framework to allow only their authorized friends to browse and search their photos using resource-bounded mobile devices. This is achieved by our carefully designed architecture and novel outsourced privacy-preserving computation protocols, through which no information about the outsourced photos or even the search contents (including the results) would be revealed to the cloud servers. Our framework is compatible with most of the existing image search technologies, and it requires few changes to the existing cloud systems. The evaluation of our prototype system with 31,772 real-life images shows the communication and computation efficiency of our system.

cs.CR↗

arXiv2014

Cloud-based Privacy Preserving Image Storage, Sharing and Search

High-resolution cameras produce huge volume of high quality images everyday. It is extremely challenging to store, share and especially search those huge images, for which increasing number of cloud services are presented to support such functionalities. However, images tend to contain rich sensitive information (\eg, people, location and event), and people's privacy concerns hinder their readily participation into the services provided by untrusted third parties. In this work, we introduce PIC: a Privacy-preserving large-scale Image search system on Cloud. Our system enables efficient yet secure content-based image search with fine-grained access control, and it also provides privacy-preserving image storage and sharing among users. Users can specify who can/cannot search on their images when using the system, and they can search on others' images if they satisfy the condition specified by the image owners. Majority of the computationally intensive jobs are outsourced to the cloud side, and users only need to submit the query and receive the result throughout the entire image search. Specially, to deal with massive images, we design our system suitable for distributed and parallel computation and introduce several optimizations to further expedite the search process. We implement a prototype of PIC including both cloud side and client side. The cloud side is a cluster of computers with distributed file system (Hadoop HDFS) and MapReduce architecture (Hadoop MapReduce). The client side is built for both Windows OS laptops and Android phones. We evaluate the prototype system with large sets of real-life photos. Our security analysis and evaluation results show that PIC successfully protect the image privacy at a low cost of computation and communication.

cs.CR↗

arXiv2014

A General Framework for Privacy-Preserving Distributed Greedy Algorithm

Increasingly more attention is paid to the privacy in online applications due to the widespread data collection for various analysis purposes. Sensitive information might be mined from the raw data during the analysis, and this led to a great privacy concern among people (data providers) these days. To deal with this privacy concerns, multitudes of privacy-preserving computation schemes are proposed to address various computation problems, and we have found many of them fall into a class of problems which can be solved by greedy algorithms. In this paper, we propose a framework for distributed greedy algorithms in which instances in the feasible set come from different parties. By our framework, most generic distributed greedy algorithms can be converted to a privacy preserving one which achieves the same result as the original greedy algorithm while the private information associated with the instances is still protected.

cs.CR↗

arXiv2013

BlueSky: Realizing Buried Potential of Bluetooth to Sustain a Large-scale Multi-hop Network

Traditionally, Bluetooth has been deemed unsuitable for sustaining a large-scale multi-hop network. There are two main reasons: severe frequency channel collisions under a large-scale network and high complexity of designing an efficient formation protocol. In this work, we reconsider this viewpoint from a practical usability perspective and aim to realize the buried potential of Bluetooth. Firstly, we find that the collision probability under a low-overhead network is fairly small, which is acceptable for practical applications. Secondly, we propose BlueSky, a complete system solution to provide necessary networking functionalities for Bluetooth. In BlueSky, we develop a connection maintenance mechanism for mitigating the influence of collisions and a network formation protocol for reliable packet transmissions. We implement BlueSky on Windows Mobile using 100 commercial smartphones. Comprehensive usability evaluations demonstrate the negligible overheads of BlueSky and its good network performance. In particular, 90%-95% of the whole 100 nodes can participate in the communication smoothly.

cs.NI↗