arXiv subjects
Publications and source records attributed to Yi Xie.
Suppose L is a link in $S^3$. We show that $π_1(S^3-L)$ admits an irreducible meridian-traceless representation in SU(2) if and only if L is not the unknot, the Hopf link, or a connected sum of Hopf links. As a corollary, $π_1(S^3-L)$ admits an irreducible representation in SU(2) if and only if L is neither the unknot nor the Hopf link. This result generalizes a theorem of Kronheimer and Mrowka to the case of links.
Deep Neural Network (DNN), one of the most powerful machine learning algorithms, is increasingly leveraged to overcome the bottleneck of effectively exploring and analyzing massive data to boost advanced scientific development. It is not a surprise that cloud computing providers offer the cloud-based DNN as an out-of-the-box service. Though there are some benefits from the cloud-based DNN, the interaction mechanism among two or multiple entities in the cloud inevitably induces new privacy risks. This survey presents the most recent findings of privacy attacks and defenses appeared in cloud-based neural network services. We systematically and thoroughly review privacy attacks and defenses in the pipeline of cloud-based DNN service, i.e., data manipulation, training, and prediction. In particular, a new theory, called cloud-based ML privacy game, is extracted from the recently published literature to provide a deep understanding of state-of-the-art research. Finally, the challenges and future work are presented to help researchers to continue to push forward the competitions between privacy attackers and defenders.
In this report, we introduce the technical details of our submission to the VIPriors object detection challenge. Our solution is based on mmdetction of a strong baseline open-source detection toolbox. Firstly, we introduce an effective data augmentation method to address the lack of data problem, which contains bbox-jitter, grid-mask, and mix-up. Secondly, we present a robust region of interest (ROI) extraction method to learn more significant ROI features via embedding global context features. Thirdly, we propose a multi-model integration strategy to refinement the prediction box, which weighted boxes fusion (WBF). Experimental results demonstrate that our approach can significantly improve the average precision (AP) of object detection on the subset of the COCO2017 dataset.
In the field of non-equilibrium phase transitions, the Kibble-Zurek mechanism (KZM) is undoubtedly an important discovery, pointing out that some universal scaling rules are applied to a wide range of physical systems from quantum to the cosmos in complex non-equilibrium continuous phase transitions. However, except for some scaling relations in specific cases, the algebraic-based KZM can not provide further details on the topological defect generation laws. In this work, we propose an analytical-based KZM that can accurately predict topological defect generation for a given quenching condition. Compared with the conventional KZM, our theory is more accurate and more widely applicable, especially in non-linear quenching conditions and inhomogeneous structural systems, where it has more obvious advantages. Our work reveals a fundamental and intrinsic mechanism in non-equilibrium phase transitions, blazing a new trail for accurate description and manipulation of topological defect generation.
Noise injection-based regularization, such as Dropout, has been widely used in image domain to improve the performance of deep neural networks (DNNs). However, efficient regularization in the point cloud domain is rarely exploited, and most of the state-of-the-art works focus on data augmentation-based regularization. In this paper, we, for the first time, perform systematic investigation on noise injection-based regularization for point cloud-domain DNNs. To be specific, we propose a series of regularization techniques, namely DropFeat, DropPoint and DropCluster, to perform noise injection on the point feature maps at the feature level, point level and cluster level, respectively. We also empirically analyze the impacts of different factors, including dropping rate, cluster size and dropping position, to obtain useful insights and general deployment guidelines, which can facilitate the adoption of our approaches across different datasets and DNN architectures. We evaluate our proposed approaches on various DNN models for different point cloud processing tasks. Experimental results show our approaches enable significant performance improvement. Notably, our DropCluster brings 1.5%, 1.3% and 0.8% higher overall accuracy for PointNet, PointNet++ and DGCNN, respectively, on ModelNet40 shape classification dataset. On ShapeNet part segmentation dataset, DropCluster brings 0.5%, 0.5% and 0.2% mean Intersection-over-union (IoU) increase for PointNet, PointNet++ and DGCNN, respectively. On S3DIS semantic segmentation dataset, DropCluster improves the mean IoU of PointNet, PointNet++ and DGCNN by 3.2%, 2.9% and 3.7%, respectively. Meanwhile, DropCluster also enables the overall accuracy increase for these three popular backbone DNNs by 2.4%, 2.2% and 1.8%, respectively.
If L is an oriented link with $n$ components, then the rank of its Khovanov homology is at least $2^n$. We classify all the links whose Khovanov homology with Z/2-coefficients achieves this lower bound, and show that such links can be obtained by iterated connected sums and disjoint unions of Hopf links and unknots. This gives a positive answer to a question asked by Batson and Seed.
Recently, the vulnerability of DNN-based audio systems to adversarial attacks has obtained the increasing attention. However, the existing audio adversarial attacks allow the adversary to possess the entire user's audio input as well as granting sufficient time budget to generate the adversarial perturbations. These idealized assumptions, however, makes the existing audio adversarial attacks mostly impossible to be launched in a timely fashion in practice (e.g., playing unnoticeable adversarial perturbations along with user's streaming input). To overcome these limitations, in this paper we propose fast audio adversarial perturbation generator (FAPG), which uses generative model to generate adversarial perturbations for the audio input in a single forward pass, thereby drastically improving the perturbation generation speed. Built on the top of FAPG, we further propose universal audio adversarial perturbation generator (UAPG), a scheme crafting universal adversarial perturbation that can be imposed on arbitrary benign audio input to cause misclassification. Extensive experiments show that our proposed FAPG can achieve up to 167X speedup over the state-of-the-art audio adversarial attack methods. Also our proposed UAPG can generate universal adversarial perturbation that achieves much better attack performance than the state-of-the-art solutions.
Decoherence induced by the laser frequency noise is one of the most important obstacles in the quantum information processing. In order to suppress this decoherence, the noise power spectral density needs to be accurately characterized. In particular, the noise spectrum measurement based on the coherence characteristics of qubits would be a meaningful and still challenging method. Here, we theoretically analyze and experimentally obtain the spectrum of laser frequency noise based on the continuous dynamical decoupling technique. We first estimate the mixture-noise (including laser and magnetic noises) spectrum up to $(2π)$530 kHz by monitoring the transverse relaxation from an initial state $+X$, followed by a gradient descent data process protocol. Then the contribution from the laser noise is extracted by enconding the qubits on different Zeeman sublevels. We also investigate two sufficiently strong noise components by making an analogy between these noises and driving lasers whose linewidth assumed to be negligible. This method is verified experimentally and finally helps to characterize the noise.
Parity-time($\mathcal{PT}$)-symmetric systems, featuring real eigenvalues despite its non-Hermitian nature, have been widely utilized to achieve exotic functionalities in the classical realm, such as loss-induced transparency or lasing revival. By approaching the exceptional point (EP) or the coalescences of both eigenvalues and eigenstates, unconventional effects are also expected to emerge in pure quantum $\mathcal{PT}$ devices. Here, we report experimental evidences of spontaneous $\mathcal{PT}$ symmetry breaking in a single cold $^{40}\mathrm{Ca}^{+}$ ion, and more importantly, a counterintuitive effect of perfect quantum coherence occurring at the EP. Excellent agreement between experimental results and theoretical predictions is identified. In view of the versatile role of cold ions in building quantum memory or processor, our experiment provides a new platform to explore and utilize pure quantum EP effects, with diverse applications in quantum engineering of trapped ions.
The form of timing residuals due to errors in pulsar spin period $P$ and its derivative $\dot{P}$, in positions, as well as in proper motions, have been well presented for decades in the literature. However, the residual patterns due to errors in the pulsar acceleration have not been reported previously, while a pulsar in the galaxy or a globular cluster (GC) will be unavoidably accelerated. The coupling effect of the pulsar transverse acceleration and the R$\rm{\ddot{o}}$mer delay on timing residuals are simulated in this work. The results show that the residual due to the effect can be identified by the oscillation envelopes of the residuals. It is also shown that the amplitude of the residual due to the effect is usually relatively small, however, it may probably be observable for pulsars distributing in the vicinity of the core of a nearby GC.
Most of the existing algorithms for traffic speed forecasting split spatial features and temporal features to independent modules, and then associate information from both dimensions. However, features from spatial and temporal dimensions influence mutually, separated extractions isolate such dependencies, and might lead to inaccurate results. In this paper, we incorporate the perspective of information diffusion to model spatial features and temporal features synchronously. Intuitively, vertices not only diffuse information to the neighborhood but also to the subsequent state along with the temporal dimension. Therefore, we can model such heterogeneous spatial-temporal structures as a homogeneous process of diffusion. On this basis, we propose an Iterative Spatial-Temporal Diffusion Graph Convolutional Network (ISTD-GCN) to extract spatial and temporal features synchronously, thus dependencies between both dimensions can be better modeled. Experiments on two traffic datasets illustrate that our ISTD-GCN outperforms 10 baselines in traffic speed forecasting tasks. The source code is available at https://github.com/Anonymous.
Existing vehicle re-identification methods commonly use spatial pooling operations to aggregate feature maps extracted via off-the-shelf backbone networks. They ignore exploring the spatial significance of feature maps, eventually degrading the vehicle re-identification performance. In this paper, firstly, an innovative spatial graph network (SGN) is proposed to elaborately explore the spatial significance of feature maps. The SGN stacks multiple spatial graphs (SGs). Each SG assigns feature map's elements as nodes and utilizes spatial neighborhood relationships to determine edges among nodes. During the SGN's propagation, each node and its spatial neighbors on an SG are aggregated to the next SG. On the next SG, each aggregated node is re-weighted with a learnable parameter to find the significance at the corresponding location. Secondly, a novel pyramidal graph network (PGN) is designed to comprehensively explore the spatial significance of feature maps at multiple scales. The PGN organizes multiple SGNs in a pyramidal manner and makes each SGN handles feature maps of a specific scale. Finally, a hybrid pyramidal graph network (HPGN) is developed by embedding the PGN behind a ResNet-50 based backbone network. Extensive experiments on three large scale vehicle databases (i.e., VeRi776, VehicleID, and VeRi-Wild) demonstrate that the proposed HPGN is superior to state-of-the-art vehicle re-identification approaches.
Asaeda, Przytycki and Sikora defined a generalization of Khovanov homology for links in $I$-bundles over compact surfaces. We prove that for a link $L\subset (-1,1)\times T^2$, the Asaeda-Przytycki-Sikora homology of $L$ has rank $2$ with $\mathbb{Z}/2$-coefficients if and only if $L$ is isotopic to an embedded knot in $\{0\}\times T^2$.
We prove that Khovanov homology with Z/2-coefficients detects the link L7n1, and the union of a trefoil and its meridian.
We classify all links whose Khovanov homology have ranks no greater than 8, and all three-component links whose Khovanov homology have ranks no greater than 12, where the coefficient ring is Z/2. The classification is based on the previous results of Kronheimer-Mrowka, Batson-Seed, Baldwin-Sivek, and the authors.
As the popularity of voice user interface (VUI) exploded in recent years, speaker recognition system has emerged as an important medium of identifying a speaker in many security-required applications and services. In this paper, we propose the first real-time, universal, and robust adversarial attack against the state-of-the-art deep neural network (DNN) based speaker recognition system. Through adding an audio-agnostic universal perturbation on arbitrary enrolled speaker's voice input, the DNN-based speaker recognition system would identify the speaker as any target (i.e., adversary-desired) speaker label. In addition, we improve the robustness of our attack by modeling the sound distortions caused by the physical over-the-air propagation through estimating room impulse response (RIR). Experiment using a public dataset of 109 English speakers demonstrates the effectiveness and robustness of our proposed attack with a high attack success rate of over 90%. The attack launching time also achieves a 100X speedup over contemporary non-universal attacks.
Deep neural network (DNN) has emerged as the most important and popular artificial intelligent (AI) technique. The growth of model size poses a key energy efficiency challenge for the underlying computing platform. Thus, model compression becomes a crucial problem. However, the current approaches are limited by various drawbacks. Specifically, network sparsification approach suffers from irregularity, heuristic nature and large indexing overhead. On the other hand, the recent structured matrix-based approach (i.e., CirCNN) is limited by the relatively complex arithmetic computation (i.e., FFT), less flexible compression ratio, and its inability to fully utilize input sparsity. To address these drawbacks, this paper proposes PermDNN, a novel approach to generate and execute hardware-friendly structured sparse DNN models using permuted diagonal matrices. Compared with unstructured sparsification approach, PermDNN eliminates the drawbacks of indexing overhead, non-heuristic compression effects and time-consuming retraining. Compared with circulant structure-imposing approach, PermDNN enjoys the benefits of higher reduction in computational complexity, flexible compression ratio, simple arithmetic computation and full utilization of input sparsity. We propose PermDNN architecture, a multi-processing element (PE) fully-connected (FC) layer-targeted computing engine. The entire architecture is highly scalable and flexible, and hence it can support the needs of different applications with different model configurations. We implement a 32-PE design using CMOS 28nm technology. Compared with EIE, PermDNN achieves 3.3x~4.8x higher throughout, 5.9x~8.5x better area efficiency and 2.8x~4.0x better energy efficiency on different workloads. Compared with CirCNN, PermDNN achieves 11.51x higher throughput and 3.89x better energy efficiency.
Deep neural networks (DNNs) are vulnerable to adversarial attack despite their tremendous success in many AI fields. Adversarial attack is a method that causes the intended misclassfication by adding imperceptible perturbations to legitimate inputs. Researchers have developed numerous types of adversarial attack methods. However, from the perspective of practical deployment, these methods suffer from several drawbacks such as long attack generating time, high memory cost, insufficient robustness and low transferability. We propose a Content-aware Adversarial Attack Generator (CAG) to achieve real-time, low-cost, enhanced-robustness and high-transferability adversarial attack. First, as a type of generative model-based attack, CAG shows significant speedup (at least 500 times) in generating adversarial examples compared to the state-of-the-art attacks such as PGD and C\&W. CAG only needs a single generative model to perform targeted attack to any targeted class. Because CAG encodes the label information into a trainable embedding layer, it differs from prior generative model-based adversarial attacks that use $n$ different copies of generative models for $n$ different targeted classes. As a result, CAG significantly reduces the required memory cost for generating adversarial examples. CAG can generate adversarial perturbations that focus on the critical areas of input by integrating the class activation maps information in the training process, and hence improve the robustness of CAG attack against the state-of-art adversarial defenses. In addition, CAG exhibits high transferability across different DNN classifier models in black-box attack scenario by introducing random dropout in the process of generating perturbations. Extensive experiments on different datasets and DNN models have verified the real-time, low-cost, enhanced-robustness, and high-transferability benefits of CAG.