arXiv subjects

Cong Wang

Publications and source records attributed to Cong Wang.

At least 343 records · Page 19Linked to original sources

arXiv2022

Aggregation Service for Federated Learning: An Efficient, Secure, and More Resilient Realization

Federated learning has recently emerged as a paradigm promising the benefits of harnessing rich data from diverse sources to train high quality models, with the salient features that training datasets never leave local devices. Only model updates are locally computed and shared for aggregation to produce a global model. While federated learning greatly alleviates the privacy concerns as opposed to learning with centralized data, sharing model updates still poses privacy risks. In this paper, we present a system design which offers efficient protection of individual model updates throughout the learning procedure, allowing clients to only provide obscured model updates while a cloud server can still perform the aggregation. Our federated learning system first departs from prior works by supporting lightweight encryption and aggregation, and resilience against drop-out clients with no impact on their participation in future rounds. Meanwhile, prior work largely overlooks bandwidth efficiency optimization in the ciphertext domain and the support of security against an actively adversarial cloud server, which we also fully explore in this paper and provide effective and efficient mechanisms. Extensive experiments over several benchmark datasets (MNIST, CIFAR-10, and CelebA) show our system achieves accuracy comparable to the plaintext baseline, with practical performance.

cs.CR↗

arXiv2022

Push-sum Distributed Dual Averaging for Convex Optimization in Multi-agent Systems with Communication Delays

The distributed convex optimization problem over the multi-agent system is considered in this paper, and it is assumed that each agent possesses its own cost function and communicates with its neighbours over a sequence of time-varying directed graphs. However, due to some reasons there exist communication delays while agents receive information from other agents, and we are going to seek the optimal value of the sum of agents' loss functions in this case. We desire to handle this problem with the push-sum distributed dual averaging (PS-DDA) algorithm. It is proved that this algorithm converges and the error decays at a rate $\mathcal{O}\left(T^{-0.5}\right)$ with proper step size, where $T$ is iteration span. The main result presented in this paper also illustrates the convergence of the proposed algorithm is related to the maximum value of the communication delay on one edge. We finally apply the theoretical results to numerical simulations to show the PS-DDA algorithm's performance.

math.OC↗

arXiv2022

Towards Private Learning on Decentralized Graphs with Local Differential Privacy

Many real-world networks are inherently decentralized. For example, in social networks, each user maintains a local view of a social graph, such as a list of friends and her profile. It is typical to collect these local views of social graphs and conduct graph learning tasks. However, learning over graphs can raise privacy concerns as these local views often contain sensitive information. In this paper, we seek to ensure private graph learning on a decentralized network graph. Towards this objective, we propose {\em Solitude}, a new privacy-preserving learning framework based on graph neural networks (GNNs), with formal privacy guarantees based on edge local differential privacy. The crux of {\em Solitude} is a set of new delicate mechanisms that can calibrate the introduced noise in the decentralized graph collected from the users. The principle behind the calibration is the intrinsic properties shared by many real-world graphs, such as sparsity. Unlike existing work on locally private GNNs, our new framework can simultaneously protect node feature privacy and edge privacy, and can seamlessly incorporate with any GNN with privacy-utility guarantees. Extensive experiments on benchmarking datasets show that {\em Solitude} can retain the generalization capability of the learned GNN while preserving the users' data privacy under given privacy budgets.

cs.LG↗

arXiv2022

An Optimization Problem in Heat Conduction With Volume Constraint and Double Obstacles

We consider the optimization problem of minimizing $\int_{\mathbb{R}^n}|\nabla u|^2\,\mathrm{d}x$ with double obstacles $ϕ\leq u\leqψ$ a.e. in $D$ and a constraint on the volume of $\{u>0\}\setminus\overline{D}$, where $D\subset\mathbb{R}^n$ is a bounded domain. By studying a penalization problem that achieves the constrained volume for small values of penalization parameter, we prove that every minimizer is $C^{1,1}$ locally in $D$ and Lipschitz continuous in $\mathbb{R}^n$ and that the free boundary $\partial\{u>0\}\setminus\overline{D}$ is smooth. Moreover, when the boundary of $D$ has a plane portion, we show that the minimizer is $C^{1,\frac{1}{2}}$ up to the plane portion.

math.AP↗

arXiv2021

TransBoost: A Boosting-Tree Kernel Transfer Learning Algorithm for Improving Financial Inclusion

The prosperity of mobile and financial technologies has bred and expanded various kinds of financial products to a broader scope of people, which contributes to advocating financial inclusion. It has non-trivial social benefits of diminishing financial inequality. However, the technical challenges in individual financial risk evaluation caused by the distinct characteristic distribution and limited credit history of new users, as well as the inexperience of newly-entered companies in handling complex data and obtaining accurate labels, impede further promoting financial inclusion. To tackle these challenges, this paper develops a novel transfer learning algorithm (i.e., TransBoost) that combines the merits of tree-based models and kernel methods. The TransBoost is designed with a parallel tree structure and efficient weights updating mechanism with theoretical guarantee, which enables it to excel in tackling real-world data with high dimensional features and sparsity in $O(n)$ time complexity. We conduct extensive experiments on two public datasets and a unique large-scale dataset from Tencent Mobile Payment. The results show that the TransBoost outperforms other state-of-the-art benchmark transfer learning algorithms in terms of prediction accuracy with superior efficiency, shows stronger robustness to data sparsity, and provides meaningful model interpretation. Besides, given a financial risk level, the TransBoost enables financial service providers to serve the largest number of users including those who would otherwise be excluded by other algorithms. That is, the TransBoost improves financial inclusion.

cs.LG↗

arXiv2021

Spin mapping of intralayer antiferromagnetism and spin-flop transition in monolayer CrTe$_2$

Intrinsic antiferromagnetism in van der Waals (vdW) monolayer (ML) crystals enriches the understanding regarding two-dimensional (2D) magnetic orders and holds special virtues over ferromagnetism in spintronic applications. However, the studies on intrinsic antiferromagnetism are sparse, owing to the lack of net magnetisation. In this study, by combining spin-polarised scanning tunnelling microscopy and first-principles calculations, we investigate the magnetism of vdW ML CrTe2, which has been successfully grown through molecular beam epitaxy. Surprisingly, we observe a stable antiferromagnetic (AFM) order at the atomic scale in the ML crystal, whose bulk is a strong ferromagnet, and correlate its imaged zigzag spin texture with the atomic lattice structure. The AFM order exhibits an intriguing noncollinear spin-flop transition under magnetic fields, consistent with its calculated moderate magnetic anisotropy. The findings of this study demonstrate the intricacy of 2D vdW magnetic materials and pave the way for their in-depth studies.

cond-mat.mtrl-sci↗

arXiv2021

On the complexity of Dark Chinese Chess

This paper provides a complexity analysis for the game of dark Chinese chess (a.k.a. "JieQi"), a variation of Chinese chess. Dark Chinese chess combines some of the most complicated aspects of board and card games, such as long-term strategy or planning, large state space, stochastic, and imperfect-information, which make it closer to the real world decision-making problem and pose great challenges to game AI. Here we design a self-play program to calculate the game tree complexity and average information set size of the game, and propose an algorithm to calculate the number of information sets.

cs.AI↗

arXiv2021

Joint space-time analyticity of mild solutions to the Navier-Stokes equations

In this paper, we show the optimal decay rate estimates of the space-time derivatives and the joint space-time analyticity of solutions to the Navier-Stokes equations. As it is known from the Hartogs's theorem, for a complex function with two complex variables, the joint analyticity with respect to two variables can be derived from combining of analyticity with respect to each variable. However, as a function of two real variables for space and time, the joint space-time analyticity of solutions to the Navier-Stokes equations cannot be directly obtained from the combination of space analyticity and time analyticity. Our result seems to be the first quantitative result for the joint space-time analyticity of solutions to the Navier-Stokes equations, and the proof only involves real variable methods. Moreover, the decay rate estimates also yield the bounds on the growth (in time) of radius of space analyticity, time analyticity, and joint space-time analyticity of solutions.

math.AP↗

arXiv2021

Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Information

Adversarial attacks against commercial black-box speech platforms, including cloud speech APIs and voice control devices, have received little attention until recent years. The current "black-box" attacks all heavily rely on the knowledge of prediction/confidence scores to craft effective adversarial examples, which can be intuitively defended by service providers without returning these messages. In this paper, we propose two novel adversarial attacks in more practical and rigorous scenarios. For commercial cloud speech APIs, we propose Occam, a decision-only black-box adversarial attack, where only final decisions are available to the adversary. In Occam, we formulate the decision-only AE generation as a discontinuous large-scale global optimization problem, and solve it by adaptively decomposing this complicated problem into a set of sub-problems and cooperatively optimizing each one. Our Occam is a one-size-fits-all approach, which achieves 100% success rates of attacks with an average SNR of 14.23dB, on a wide range of popular speech and speaker recognition APIs, including Google, Alibaba, Microsoft, Tencent, iFlytek, and Jingdong, outperforming the state-of-the-art black-box attacks. For commercial voice control devices, we propose NI-Occam, the first non-interactive physical adversarial attack, where the adversary does not need to query the oracle and has no access to its internal information and training data. We combine adversarial attacks with model inversion attacks, and thus generate the physically-effective audio AEs with high transferability without any interaction with target devices. Our experimental results show that NI-Occam can successfully fool Apple Siri, Microsoft Cortana, Google Assistant, iFlytek and Amazon Echo with an average SRoA of 52% and SNR of 9.65dB, shedding light on non-interactive physical attacks against voice control devices.

cs.CR↗

arXiv2021

ShieldDB: An Encrypted Document Database with Padding Countermeasures

The security of our data stores is underestimated in current practice, which resulted in many large-scale data breaches. To change the status quo, this paper presents the design of ShieldDB, an encrypted document database. ShieldDB adapts the searchable encryption technique to preserve the search functionality over encrypted documents without having much impact on its scalability. However, merely realising such a theoretical primitive suffers from real-world threats, where a knowledgeable adversary can exploit the leakage (aka access pattern to the database) to break the claimed protection on data confidentiality. To address this challenge in practical deployment, ShieldDB is designed with tailored padding countermeasures. Unlike prior works, we target a more realistic adversarial model, where the database gets updated continuously, and the adversary can monitor it at an (or multiple) arbitrary time interval(s). ShieldDB's padding strategies ensure that the access pattern to the database is obfuscated all the time. Additionally, ShieldDB provides other advanced features, including forward privacy, re-encryption, and flushing, to further improve its security and efficiency. We present a full-fledged implementation of ShieldDB and conduct intensive evaluations on Azure Cloud.

cs.CR↗

arXiv2021

Optimizing Secure Decision Tree Inference Outsourcing

Outsourcing decision tree inference services to the cloud is highly beneficial, yet raises critical privacy concerns on the proprietary decision tree of the model provider and the private input data of the client. In this paper, we design, implement, and evaluate a new system that allows highly efficient outsourcing of decision tree inference. Our system significantly improves upon the state-of-the-art in the overall online end-to-end secure inference service latency at the cloud as well as the local-side performance of the model provider. We first presents a new scheme which securely shifts most of the processing of the model provider to the cloud, resulting in a substantial reduction on the model provider's performance complexities. We further devise a scheme which substantially optimizes the performance for encrypted decision tree inference at the cloud, particularly the communication round complexities. The synergy of these techniques allows our new system to achieve up to $8 \times$ better overall online end-to-end secure inference latency at the cloud side over realistic WAN environment, as well as bring the model provider up to $19 \times$ savings in communication and $18 \times$ savings in computation.

cs.CR↗

arXiv2021

Chirality locking charge density waves in a chiral crystal

In Weyl semimetals, charge density wave (CDW) order can spontaneously break the chiral symmetry, gap out the Weyl nodes, and drive the material into the axion insulating phase. Investigations have however been limited since CDWs are rarely seen in Weyl semimetals. Here, using scanning tunneling microscopy/spectroscopy, we report the discovery of a novel unidirectional CDW order on the (001) surface of chiral crystal CoSi - a unique Weyl semimetal with unconventional chiral fermions. The CDW is incommensurate with both lattice momentum and crystalline symmetry directions, and exhibits an intra unit cell π phase shift in the layer stacking direction. The tunneling spectrum shows a particle-hole asymmetric V-shaped energy gap around the Fermi level that modulates spatially with the CDW wave vector. Combined with first-principle calculations, we identify that the CDW is locked to the crystal chirality and is related by a mirror reflection between the two enantiomers of the chiral crystal. Our findings reveal a novel correlated topological quantum state in chiral CoSi crystals and raise the potential for realizing an axion insulator and exploring the unprecedented physical behaviors of unconventional chiral fermions.

cond-mat.mtrl-sci↗

arXiv2021

Scalable massively parallel computing using continuous-time data representation in nanoscale crossbar array

The growth of connected intelligent devices in the Internet of Things has created a pressing need for real-time processing and understanding of large volumes of analogue data. The difficulty in boosting the computing speed renders digital computing unable to meet the demand for processing analogue information that is intrinsically continuous in magnitude and time. By utilizing a continuous data representation in a nanoscale crossbar array, parallel computing can be implemented for the direct processing of analogue information in real time. Here, we propose a scalable massively parallel computing scheme by exploiting a continuous-time data representation and frequency multiplexing in a nanoscale crossbar array. This computing scheme enables the parallel reading of stored data and the one-shot operation of matrix-matrix multiplications in the crossbar array. Furthermore, we achieve the one-shot recognition of 16 letter images based on two physically interconnected crossbar arrays and demonstrate that the processing and modulation of analogue information can be simultaneously performed in a memristive crossbar array.

cond-mat.mtrl-sci↗

arXiv2021

TDLS: A Top-Down Layer Searching Algorithm for Generating Counterfactual Visual Explanation

Explanation of AI, as well as fairness of algorithms' decisions and the transparency of the decision model, are becoming more and more important. And it is crucial to design effective and human-friendly techniques when opening the black-box model. Counterfactual conforms to the human way of thinking and provides a human-friendly explanation, and its corresponding explanation algorithm refers to a strategic alternation of a given data point so that its model output is "counter-facted", i.e. the prediction is reverted. In this paper, we adapt counterfactual explanation over fine-grained image classification problem. We demonstrated an adaptive method that could give a counterfactual explanation by showing the composed counterfactual feature map using top-down layer searching algorithm (TDLS). We have proved that our TDLS algorithm could provide more flexible counterfactual visual explanation in an efficient way using VGG-16 model on Caltech-UCSD Birds 200 dataset. At the end, we discussed several applicable scenarios of counterfactual visual explanations.

cs.CV↗

arXiv2021

Fully Non-Homogeneous Atmospheric Scattering Modeling with Convolutional Neural Networks for Single Image Dehazing

In recent years, single image dehazing models (SIDM) based on atmospheric scattering model (ASM) have achieved remarkable results. However, it is noted that ASM-based SIDM degrades its performance in dehazing real world hazy images due to the limited modelling ability of ASM where the atmospheric light factor (ALF) and the angular scattering coefficient (ASC) are assumed as constants for one image. Obviously, the hazy images taken in real world cannot always satisfy this assumption. Such generating modelling mismatch between the real-world images and ASM sets up the upper bound of trained ASM-based SIDM for dehazing. Bearing this in mind, in this study, a new fully non-homogeneous atmospheric scattering model (FNH-ASM) is proposed for well modeling the hazy images under complex conditions where ALF and ASC are pixel dependent. However, FNH-ASM brings difficulty in practical application. In FNH-ASM based SIDM, the estimation bias of parameters at different positions lead to different distortion of dehazing result. Hence, in order to reduce the influence of parameter estimation bias on dehazing results, two new cost sensitive loss functions, beta-Loss and D-Loss, are innovatively developed for limiting the parameter bias of sensitive positions that have a greater impact on the dehazing result. In the end, based on FNH-ASM, an end-to-end CNN-based dehazing network, FNHD-Net, is developed, which applies beta-Loss and D-Loss. Experimental results demonstrate the effectiveness and superiority of our proposed FNHD-Net for dehazing on both synthetic and real-world images. And the performance improvement of our method increases more obviously in dense and heterogeneous haze scenes.

cs.CV↗

arXiv2021

Rates of convergence of the partial-wave expansion beyond Kato's cusp condition II: evaluations for the prefactors on the ground state of the helium atom

This article is a continuation of our previous work (Phys. Rev. A 88, 032511 (2013)). The prefactors for the partial-wave expansion of the helium atom are derived. Due to series of cancellations, the partial-wave increments of the energy converge as $L^{-2N-6}$. The origin of these cancellations is identified from alternative expressions of the partial-wave energies. There is some evidence that the assumptions of regularities for the exact wavefunction can be reduced.

physics.atom-ph↗

arXiv2021

Securing Face Liveness Detection Using Unforgeable Lip Motion Patterns

Face authentication usually utilizes deep learning models to verify users with high recognition accuracy. However, face authentication systems are vulnerable to various attacks that cheat the models by manipulating the digital counterparts of human faces. So far, lots of liveness detection schemes have been developed to prevent such attacks. Unfortunately, the attacker can still bypass these schemes by constructing wide-ranging sophisticated attacks. We study the security of existing face authentication services (e.g., Microsoft, Amazon, and Face++) and typical liveness detection approaches. Particularly, we develop a new type of attack, i.e., the low-cost 3D projection attack that projects manipulated face videos on a 3D face model, which can easily evade these face authentication services and liveness detection approaches. To this end, we propose FaceLip, a novel liveness detection scheme for face authentication, which utilizes unforgeable lip motion patterns built upon well-designed acoustic signals to enable a strong security guarantee. The unique lip motion patterns for each user are unforgeable because FaceLip verifies the patterns by capturing and analyzing the acoustic signals that are dynamically generated according to random challenges, which ensures that our signals for liveness detection cannot be manipulated. Specially, we develop robust algorithms for FaceLip to eliminate the impact of noisy signals in the environment and thus can accurately infer the lip motions at larger distances. We prototype FaceLip on off-the-shelf smartphones and conduct extensive experiments under different settings. Our evaluation with 44 participants validates the effectiveness and robustness of FaceLip.

cs.CR↗

arXiv2021

CARTL: Cooperative Adversarially-Robust Transfer Learning

Transfer learning eases the burden of training a well-performed model from scratch, especially when training data is scarce and computation power is limited. In deep learning, a typical strategy for transfer learning is to freeze the early layers of a pre-trained model and fine-tune the rest of its layers on the target domain. Previous work focuses on the accuracy of the transferred model but neglects the transfer of adversarial robustness. In this work, we first show that transfer learning improves the accuracy on the target domain but degrades the inherited robustness of the target model. To address such a problem, we propose a novel cooperative adversarially-robust transfer learning (CARTL) by pre-training the model via feature distance minimization and fine-tuning the pre-trained model with non-expansive fine-tuning for target domain tasks. Empirical results show that CARTL improves the inherited robustness by about 28% at most compared with the baseline with the same degree of accuracy. Furthermore, we study the relationship between the batch normalization (BN) layers and the robustness in the context of transfer learning, and we reveal that freezing BN layers can further boost the robustness transfer.

cs.LG↗