arXiv subjects

Qing Liao

Publications and source records attributed to Qing Liao.

At least 55 records · Page 3Linked to original sources

arXiv2023

Deep Intellectual Property Protection: A Survey

Deep Neural Networks (DNNs), from AlexNet to ResNet to ChatGPT, have made revolutionary progress in recent years, and are widely used in various fields. The high performance of DNNs requires a huge amount of high-quality data, expensive computing hardware, and excellent DNN architectures that are costly to obtain. Therefore, trained DNNs are becoming valuable assets and must be considered the Intellectual Property (IP) of the legitimate owner who created them, in order to protect trained DNN models from illegal reproduction, stealing, redistribution, or abuse. Although being a new emerging and interdisciplinary field, numerous DNN model IP protection methods have been proposed. Given this period of rapid evolution, the goal of this paper is to provide a comprehensive survey of two mainstream DNN IP protection methods: deep watermarking and deep fingerprinting, with a proposed taxonomy. More than 190 research contributions are included in this survey, covering many aspects of Deep IP Protection: problem definition, main threats and challenges, merits and demerits of deep watermarking and deep fingerprinting methods, evaluation metrics, and performance discussion. We finish the survey by identifying promising directions for future research.

cs.AI↗

arXiv2023

LIVABLE: Exploring Long-Tailed Classification of Software Vulnerability Types

Prior studies generally focus on software vulnerability detection and have demonstrated the effectiveness of Graph Neural Network (GNN)-based approaches for the task. Considering the various types of software vulnerabilities and the associated different degrees of severity, it is also beneficial to determine the type of each vulnerable code for developers. In this paper, we observe that the distribution of vulnerability type is long-tailed in practice, where a small portion of classes have massive samples (i.e., head classes) but the others contain only a few samples (i.e., tail classes). Directly adopting previous vulnerability detection approaches tends to result in poor detection performance, mainly due to two reasons. First, it is difficult to effectively learn the vulnerability representation due to the over-smoothing issue of GNNs. Second, vulnerability types in tails are hard to be predicted due to the extremely few associated samples.To alleviate these issues, we propose a Long-taIled software VulnerABiLity typE classification approach, called LIVABLE. LIVABLE mainly consists of two modules, including (1) vulnerability representation learning module, which improves the propagation steps in GNN to distinguish node representations by a differentiated propagation method. A sequence-to-sequence model is also involved to enhance the vulnerability representations. (2) adaptive re-weighting module, which adjusts the learning weights for different types according to the training epochs and numbers of associated samples by a novel training loss.

cs.SE↗

arXiv2023

RARE: Robust Masked Graph Autoencoder

Masked graph autoencoder (MGAE) has emerged as a promising self-supervised graph pre-training (SGP) paradigm due to its simplicity and effectiveness. However, existing efforts perform the mask-then-reconstruct operation in the raw data space as is done in computer vision (CV) and natural language processing (NLP) areas, while neglecting the important non-Euclidean property of graph data. As a result, the highly unstable local connection structures largely increase the uncertainty in inferring masked data and decrease the reliability of the exploited self-supervision signals, leading to inferior representations for downstream evaluations. To address this issue, we propose a novel SGP method termed Robust mAsked gRaph autoEncoder (RARE) to improve the certainty in inferring masked data and the reliability of the self-supervision mechanism by further masking and reconstructing node samples in the high-order latent feature space. Through both theoretical and empirical analyses, we have discovered that performing a joint mask-then-reconstruct strategy in both latent feature and raw data spaces could yield improved stability and performance. To this end, we elaborately design a masked latent feature completion scheme, which predicts latent features of masked nodes under the guidance of high-order sample correlations that are hard to be observed from the raw data perspective. Specifically, we first adopt a latent feature predictor to predict the masked latent features from the visible ones. Next, we encode the raw data of masked samples with a momentum graph encoder and subsequently employ the resulting representations to improve predicted results through latent feature matching. Extensive experiments on seventeen datasets have demonstrated the effectiveness and robustness of RARE against state-of-the-art (SOTA) competitors across three downstream tasks.

cs.LG↗

arXiv2023

Vulnerability Detection with Graph Simplification and Enhanced Graph Representation Learning

Prior studies have demonstrated the effectiveness of Deep Learning (DL) in automated software vulnerability detection. Graph Neural Networks (GNNs) have proven effective in learning the graph representations of source code and are commonly adopted by existing DL-based vulnerability detection methods. However, the existing methods are still limited by the fact that GNNs are essentially difficult to handle the connections between long-distance nodes in a code structure graph. Besides, they do not well exploit the multiple types of edges in a code structure graph (such as edges representing data flow and control flow). Consequently, despite achieving state-of-the-art performance, the existing GNN-based methods tend to fail to capture global information (i.e., long-range dependencies among nodes) of code graphs. To mitigate these issues, in this paper, we propose a novel vulnerability detection framework with grAph siMplification and enhanced graph rePresentation LEarning, named AMPLE. AMPLE mainly contains two parts: 1) graph simplification, which aims at reducing the distances between nodes by shrinking the node sizes of code structure graphs; 2) enhanced graph representation learning, which involves one edge-aware graph convolutional network module for fusing heterogeneous edge information into node representations and one kernel-scaled representation module for well capturing the relations between distant graph nodes. Experiments on three public benchmark datasets show that AMPLE outperforms the state-of-the-art methods by 0.39%-35.32% and 7.64%-199.81% with respect to the accuracy and F1 score metrics, respectively. The results demonstrate the effectiveness of AMPLE in learning global information of code graphs for vulnerability detection.

cs.SE↗

arXiv2022

Circularly Polarized Lasing from a Microcavity Filled with Achiral Single-Crystalline Microribbons

Organic circularly polarized (CP) lasers have received increasing attention due to their future photoelectric applications. Here, we demonstrate a CP laser from a pure organic crystal-filled microcavity without any chiral molecules or chiral structures. Benefited from the giant anisotropy and excellent laser gain of organic crystals, optical Rashba-Dresselhaus spin-orbit coupling effect can be induced and is conductive to the CP laser in such microcavities. The maximum dissymmetry factor of the CP lasing with opposite helicities reached, is as high as 1.2. Our strategy may provide a new idea for the design of CP lasers towards future 3D laser displays, information storage and other fields.

physics.optics↗

arXiv2022

A room-temperature electrical-field-enhanced ultrafast switch in organic microcavity polariton condensates

Integrated electro-optical switches are essential as one of the fundamental elements in the development of modern optoelectronics. As an architecture for photonic systems, exciton polaritons, that are hybrid bosonic quasiparticles that possess unique properties derived from both excitons and photons, have shown much promise. For this system, we demonstrate a significant improvement of emitted intensity and condensation threshold by applying an electric field to a microcavity filled with an organic microbelt. Our theoretical investigations indicate that the electric field makes the excitons dipolar and induces an enhancement of the exciton-polariton interaction and of the polariton lifetime. Based on these electric field induced changes, a sub-nanosecond electrical-field-enhanced polariton condensate switch is realized at room temperature, providing the basis for developing an on-chip integrated photonic device in the strong light-matter coupling regime.

physics.optics↗

arXiv2022

Circularly polarized electroluminescence from a single-crystal organic microcavity light-emitting diode based on photonic spin-orbit interactions

Circularly polarized (CP) electroluminescence from organic light-emitting diodes (OLEDs) has aroused considerable attention for their potential in future display and photonic technologies. The development of CP-OLEDs relies largely on chiral-emitters, which not only remain rare owing to difficulties in design and synthesis but also limit the performance of electroluminescence. When the polarization (pseudospin) degrees of freedom of a photon interact with its orbital angular momentum, photonic spin-orbit interaction (SOI) emerges such as Rashba-Dresselhaus (RD) effect. Here, we demonstrate a chiral-emitter-free microcavity CP-OLED with a high dissymmetry factor (gEL) and high luminance by embedding a thin two-dimensional organic single crystal (2D-OSC) between two silver layers which serve as two metallic mirrors forming a microcavity and meanwhile also as two electrodes in an OLED architecture. In the presence of the RD effect, the SOIs in the birefringent 2D-OSC microcavity result in a controllable spin-splitting with CP dispersions. Thanks to the high emission efficiency and high carrier mobility of the OSC, chiral-emitter-free CP-OLEDs have been demonstrated exhibiting a high gEL of 1.1 and a maximum luminance of about 60000 cd/m2, which places our device among the best performing CP-OLEDs. This strategy opens a new avenue for practical applications towards on-chip microcavity CP-OLEDs.

physics.optics↗

arXiv2022

Listening to Users' Voice: Automatic Summarization of Helpful App Reviews

App reviews are crowdsourcing knowledge of user experience with the apps, providing valuable information for app release planning, such as major bugs to fix and important features to add. There exist prior explorations on app review mining for release planning, however, most of the studies strongly rely on pre-defined classes or manually-annotated reviews. Also, the new review characteristic, i.e., the number of users who rated the review as helpful, which can help capture important reviews, has not been considered previously. In the paper, we propose a novel framework, named SOLAR, aiming at accurately summarizing helpful user reviews to developers. The framework mainly contains three modules: The review helpfulness prediction module, topic-sentiment modeling module, and multi-factor ranking module. The review helpfulness prediction module assesses the helpfulness of reviews, i.e., whether the review is useful for developers. The topic-sentiment modeling module groups the topics of the helpful reviews and also predicts the associated sentiment, and the multi-factor ranking module aims at prioritizing semantically representative reviews for each topic as the review summary. Experiments on five popular apps indicate that SOLAR is effective for review summarization and promising for facilitating app release planning.

cs.SE↗

arXiv2022

Knowledge-aware Neural Networks with Personalized Feature Referencing for Cold-start Recommendation

Incorporating knowledge graphs (KGs) as side information in recommendation has recently attracted considerable attention. Despite the success in general recommendation scenarios, prior methods may fall short of performance satisfaction for the cold-start problem in which users are associated with very limited interactive information. Since the conventional methods rely on exploring the interaction topology, they may however fail to capture sufficient information in cold-start scenarios. To mitigate the problem, we propose a novel Knowledge-aware Neural Networks with Personalized Feature Referencing Mechanism, namely KPER. Different from most prior methods which simply enrich the targets' semantics from KGs, e.g., product attributes, KPER utilizes the KGs as a "semantic bridge" to extract feature references for cold-start users or items. Specifically, given cold-start targets, KPER first probes semantically relevant but not necessarily structurally close users or items as adaptive seeds for referencing features. Then a Gated Information Aggregation module is introduced to learn the combinatorial latent features for cold-start users and items. Our extensive experiments over four real-world datasets show that, KPER consistently outperforms all competing methods in cold-start scenarios, whilst maintaining superiority in general scenarios without compromising overall performance, e.g., by achieving 0.81%-16.08% and 1.01%-14.49% performance improvement across all datasets in Top-10 recommendation.

cs.IR↗

arXiv2022

On the Equity of Nuclear Norm Maximization in Unsupervised Domain Adaptation

Nuclear norm maximization has shown the power to enhance the transferability of unsupervised domain adaptation model (UDA) in an empirical scheme. In this paper, we identify a new property termed equity, which indicates the balance degree of predicted classes, to demystify the efficacy of nuclear norm maximization for UDA theoretically. With this in mind, we offer a new discriminability-and-equity maximization paradigm built on squares loss, such that predictions are equalized explicitly. To verify its feasibility and flexibility, two new losses termed Class Weighted Squares Maximization (CWSM) and Normalized Squares Maximization (NSM), are proposed to maximize both predictive discriminability and equity, from the class level and the sample level, respectively. Importantly, we theoretically relate these two novel losses (i.e., CWSM and NSM) to the equity maximization under mild conditions, and empirically suggest the importance of the predictive equity in UDA. Moreover, it is very efficient to realize the equity constraints in both losses. Experiments of cross-domain image classification on three popular benchmark datasets show that both CWSM and NSM contribute to outperforming the corresponding counterparts.

cs.CV↗

arXiv2021

Helical polariton lasing from topological valleys in an organic crystalline microcavity

Topological photonics provides an important platform for the development of photonic devices with robust disorder-immune light transport and controllable helicity. Mixing photons with excitons (or polaritons) gives rise to nontrivial polaritonic bands with chiral modes, allowing the manipulation of helical lasers in strongly coupled light-matter systems. In this work, we demonstrate helical polariton lasing from topological valleys of an organic anisotropic microcrystalline cavity based on tailored local nontrivial band geometry. This polariton laser emits light of different helicity along different angular directions. The significantly enhanced chiral characteristics are achieved by the nonlinear relaxation process. Helical topological polariton lasers may provide a perfect platform for the exploration of novel topological phenomena that involve light-matter interaction and the development of polariton-based spintronic devices.

physics.optics↗

arXiv2021

CGNN: Traffic Classification with Graph Neural Network

Traffic classification associates packet streams with known application labels, which is vital for network security and network management. With the rise of NAT, port dynamics, and encrypted traffic, it is increasingly challenging to obtain unified traffic features for accurate classification. Many state-of-the-art traffic classifiers automatically extract features from the packet stream based on deep learning models such as convolution networks. Unfortunately, the compositional and causal relationships between packets are not well extracted in these deep learning models, which affects both prediction accuracy and generalization on different traffic types. In this paper, we present a chained graph model on the packet stream to keep the chained compositional sequence. Next, we propose CGNN, a graph neural network based traffic classification method, which builds a graph classifier over automatically extracted features over the chained graph. Extensive evaluation over real-world traffic data sets, including normal, encrypted and malicious labels, show that, CGNN improves the prediction accuracy by 23\% to 29\% for application classification, by 2\% to 37\% for malicious traffic classification, and reaches the same accuracy level for encrypted traffic classification. CGNN is quite robust in terms of the recall and precision metrics. We have extensively evaluated the parameter sensitivity of CGNN, which yields optimized parameters that are quite effective for traffic classification.

cs.LG↗

arXiv2021

Pixel Difference Networks for Efficient Edge Detection

Recently, deep Convolutional Neural Networks (CNNs) can achieve human-level performance in edge detection with the rich and abstract edge representation capacities. However, the high performance of CNN based edge detection is achieved with a large pretrained CNN backbone, which is memory and energy consuming. In addition, it is surprising that the previous wisdom from the traditional edge detectors, such as Canny, Sobel, and LBP are rarely investigated in the rapid-developing deep learning era. To address these issues, we propose a simple, lightweight yet effective architecture named Pixel Difference Network (PiDiNet) for efficient edge detection. Extensive experiments on BSDS500, NYUD, and Multicue are provided to demonstrate its effectiveness, and its high training and inference efficiency. Surprisingly, when training from scratch with only the BSDS500 and VOC datasets, PiDiNet can surpass the recorded result of human perception (0.807 vs. 0.803 in ODS F-measure) on the BSDS500 dataset with 100 FPS and less than 1M parameters. A faster version of PiDiNet with less than 0.1M parameters can still achieve comparable performance among state of the arts with 200 FPS. Results on the NYUD and Multicue datasets show similar observations. The codes are available at https://github.com/zhuoinoulu/pidinet.

cs.CV↗

arXiv2021

Realization of exciton-mediated optical spin-orbit interaction in organic microcrystalline resonators

The ability to control the spin-orbit interaction of light in optical microresonators is of fundamental importance for future photonics. Organic microcrystals, due to their giant optical anisotropy, play a crucial role in spin-optics and topological photonics. Here we realize controllable and wavelength-dependent Rashba-Dresselhaus spin-orbit interaction, attributed to the anisotropic excitonic response in an optical microcavity filled with an organic microcrystalline. We also investigate the transition of the spin-orbit interaction from dominant photonic type caused by the splitting of the transverse-electric and transverse-magnetic modes to spin-orbit interaction of the Rashba-Dresselhaus type. The interplay of the two allows us to engineer the spin-orbit interaction of light in organic microcavities, which besides its fundamental interest promises applications in spin-controlled on-chip integrated nanophotonic elements, towards exploiting non-magnetic and low-cost spin-photonic devices.

physics.optics↗

arXiv2020

Experimental measurement of the divergent quantum metric of an exceptional point

The geometry of Hamiltonian's eigenstates is encoded in the quantum geometric tensor (QGT). It contains both the Berry curvature, central to the description of topological matter and the quantum metric. So far the full QGT has been measured only in Hermitian systems, where the role of the quantum metric is mostly shown to determine corrections to physical effects. On the contrary, in non-Hermitian systems, and in particular near exceptional points, the quantum metric is expected to diverge and to often play a dominant role, for example on the enhanced sensing and on wave packet dynamics. In this work, we report the first experimental measurement of the quantum metric in a non-Hermitian system. The specific platform under study is an organic microcavity with exciton-polariton eigenstates, which demonstrate exceptional points. We measure the quantum metric's divergence and we determine the scaling exponent $n=-1.01\pm0.08$, which is in agreement with theoretical predictions for the second-order exceptional points.

cond-mat.mes-hall↗

arXiv2019

Nontrivial band geometry in an optically active system

Optical activity (OA), also called circular birefringence, is known for two hundred years, but its applications for topological photonics remain unexplored. Unlike the Faraday effect, OA provokes rotation of the linear polarization of light without magnetic effects, thus preserving the time-reversal symmetry. Here, we report a direct measurement of the Berry curvature and quantum metric of the photonic modes of a planar cavity containing an optically active organic microcrystal (perylene). Photonic spin-orbit-coupling induced by the cavity results in the action of a non-Abelian gauge field on photons. The addition of high OA makes emerge geometrically non-trivial bands containing two gapped Dirac cones with opposite topological charges. This experiment performed at room temperature and at visible wavelength establishes the potential of optically active organic materials for implementing non-magnetic and low-cost topological photonic devices.

cond-mat.mes-hall↗

arXiv2019

General Proximal Incremental Aggregated Gradient Algorithms: Better and Novel Results under General Scheme

The incremental aggregated gradient algorithm is popular in network optimization and machine learning research. However, the current convergence results require the objective function to be strongly convex. And the existing convergence rates are also limited to linear convergence. Due to the mathematical techniques, the stepsize in the algorithm is restricted by the strongly convex constant, which may make the stepsize be very small (the strongly convex constant may be small). In this paper, we propose a general proximal incremental aggregated gradient algorithm, which contains various existing algorithms including the basic incremental aggregated gradient method. Better and new convergence results are proved even with the general scheme. The novel results presented in this paper, which have not appeared in previous literature, include: a general scheme, nonconvex analysis, the sublinear convergence rates of the function values, much larger stepsizes that guarantee the convergence, the convergence when noise exists, the line search strategy of the proximal incremental aggregated gradient algorithm and its convergence.

math.OC↗

arXiv2018

Positioning of Transparent Targets Using Defocusing Method in a Laser Proton Accelerator

We report a positioning method for transparent targets with an accuracy of \SI{2}{μm} for a compact laser proton accelerator. The positioning system consists of two light-emitting diodes (LED), a long working distance objective and two charge coupled devices (CCD) for illumination, imaging and detection, respectively. We developed a defocusing method making transparent targets visible as phase objects and applied it to our system. Precise positioning of transparent targets can be realized by means of minimizing the image contrast of the phase objects. Fast positioning based on the relationship between the radius of spherical aberration ring and defocusing distance is also realized. Laser proton acceleration experiments have been performed to demonstrate the reliability of this positioning system.

physics.app-ph↗