Searcharxiv⌕ Search

arXiv subjects

Cheng Wang

Publications and source records attributed to Cheng Wang.

At least 289 records · Page 16Linked to original sources
arXiv2023

Enhancing Exfiltration Path Analysis Using Reinforcement Learning

Building on previous work using reinforcement learning (RL) focused on identification of exfiltration paths, this work expands the methodology to include protocol and payload considerations. The former approach to exfiltration path discovery, where reward and state are associated specifically with the determination of optimal paths, are presented with these additional realistic characteristics to account for nuances in adversarial behavior. The paths generated are enhanced by including communication payload and protocol into the Markov decision process (MDP) in order to more realistically emulate attributes of network based exfiltration events. The proposed method will help emulate complex adversarial considerations such as the size of a payload being exported over time or the protocol on which it occurs, as is the case where threat actors steal data over long periods of time using system native ports or protocols to avoid detection. As such, practitioners will be able to improve identification of expected adversary behavior under various payload and protocol assumptions more comprehensively.

cs.CR↗
arXiv2023

Deep photonic reservoir computing recurrent network

Deep neural networks usually process information through multiple hidden layers. However, most hardware reservoir computing recurrent networks only have one hidden reservoir layer, which significantly limits the capability of solving real-world complex tasks. Here we show a deep photonic reservoir computing (PRC) architecture, which is constructed by cascading injection-locked semiconductor lasers. In particular, the connection between successive hidden layers is all optical, without any optical-electrical conversion or analog-digital conversion. The proof of concept is demonstrated on a PRC consisting of 4 hidden layers and 320 interconnected neurons. In addition, we apply the deep PRC in the real-world signal equalization of an optical fiber communication system. It is found that the deep PRC owns strong ability to compensate the nonlinearity of fibers.

physics.optics↗
arXiv2023

Cross-temporal Detection of Novel Ransomware Campaigns: A Multi-Modal Alert Approach

We present a novel approach to identify ransomware campaigns derived from attack timelines representations within victim networks. Malicious activity profiles developed from multiple alert sources support the construction of alert graphs. This approach enables an effective and scalable representation of the attack timelines where individual nodes represent malicious activity detections with connections describing the potential attack paths. This work demonstrates adaptability to different attack patterns through implementing a novel method for parsing and classifying alert graphs while maintaining efficacy despite potentially low-dimension node features.

cs.CR↗
arXiv2023

Decoupled Local Aggregation for Point Cloud Learning

The unstructured nature of point clouds demands that local aggregation be adaptive to different local structures. Previous methods meet this by explicitly embedding spatial relations into each aggregation process. Although this coupled approach has been shown effective in generating clear semantics, aggregation can be greatly slowed down due to repeated relation learning and redundant computation to mix directional and point features. In this work, we propose to decouple the explicit modelling of spatial relations from local aggregation. We theoretically prove that basic neighbor pooling operations can too function without loss of clarity in feature fusion, so long as essential spatial information has been encoded in point features. As an instantiation of decoupled local aggregation, we present DeLA, a lightweight point network, where in each learning stage relative spatial encodings are first formed, and only pointwise convolutions plus edge max-pooling are used for local aggregation then. Further, a regularization term is employed to reduce potential ambiguity through the prediction of relative coordinates. Conceptually simple though, experimental results on five classic benchmarks demonstrate that DeLA achieves state-of-the-art performance with reduced or comparable latency. Specifically, DeLA achieves over 90\% overall accuracy on ScanObjectNN and 74\% mIoU on S3DIS Area 5. Our code is available at https://github.com/Matrix-ASC/DeLA .

cs.CV↗
arXiv2023

Teeth And Root Canals Segmentation Using ZXYFormer With Uncertainty Guidance And Weight Transfer

This study attempts to segment teeth and root-canals simultaneously from CBCT images, but there are very challenging problems in this process. First, the clinical CBCT image data is very large (e.g., 672 *688 * 688), and the use of downsampling operation will lose useful information about teeth and root canals. Second, teeth and root canals are very different in morphology, and it is difficult for a simple network to identify them precisely. In addition, there are weak edges at the tooth, between tooth and root canal, which makes it very difficult to segment such weak edges. To this end, we propose a coarse-to-fine segmentation method based on inverse feature fusion transformer and uncertainty estimation to address above challenging problems. First, we use the downscaled volume data (e.g., 128 * 128 * 128) to conduct coarse segmentation and map it to the original volume to obtain the area of teeth and root canals. Then, we design a transformer with reverse feature fusion, which can bring better segmentation effect of different morphological objects by transferring deeper features to shallow features. Finally, we design an auxiliary branch to calculate and refine the difficult areas in order to improve the weak edge segmentation performance of teeth and root canals. Through the combined tooth and root canal segmentation experiment of 157 clinical high-resolution CBCT data, it is verified that the proposed method is superior to the existing tooth or root canal segmentation methods.

cs.CV↗
arXiv2023

The Application of Driver Models in the Safety Assessment of Autonomous Vehicles: A Survey

Driver models play a vital role in developing and verifying autonomous vehicles (AVs). Previously, they are mainly applied in traffic flow simulation to model driver behavior. With the development of AVs, driver models attract much attention again due to their potential contributions to AV safety assessment. The simulation-based testing method is an effective measure to accelerate AV testing due to its safe and efficient characteristics. Nonetheless, realistic driver models are prerequisites for valid simulation results. Additionally, an AV is assumed to be at least as safe as a careful and competent driver, which is modeled by driver models as well. Therefore, driver models are essential for AV safety assessment from the current perspective. However, no comparison or discussion of driver models is available regarding their utility to AVs in the last five years despite their necessities in the release of AVs. This motivates us to present a comprehensive survey of driver models in the paper and compare their applicability. Requirements for driver models as applied to AV safety assessment are discussed. A summary of driver models for simulation-based testing and AV benchmarks is provided. Evaluation metrics are defined to compare their strength and weakness. Finally, potential gaps in existing driver models are identified, which provide direction for future work. This study gives related researchers especially regulators an overview and helps them to define appropriate driver models for AVs.

cs.RO↗
arXiv2023

Evaluation of STT-MRAM as a Scratchpad for Training in ML Accelerators

Progress in artificial intelligence and machine learning over the past decade has been driven by the ability to train larger deep neural networks (DNNs), leading to a compute demand that far exceeds the growth in hardware performance afforded by Moore's law. Training DNNs is an extremely memory-intensive process, requiring not just the model weights but also activations and gradients for an entire minibatch to be stored. The need to provide high-density and low-leakage on-chip memory motivates the exploration of emerging non-volatile memory for training accelerators. Spin-Transfer-Torque MRAM (STT-MRAM) offers several desirable properties for training accelerators, including 3-4x higher density than SRAM, significantly reduced leakage power, high endurance and reasonable access time. On the one hand, MRAM write operations require high write energy and latency due to the need to ensure reliable switching. In this study, we perform a comprehensive device-to-system evaluation and co-optimization of STT-MRAM for efficient ML training accelerator design. We devised a cross-layer simulation framework to evaluate the effectiveness of STT-MRAM as a scratchpad replacing SRAM in a systolic-array-based DNN accelerator. To address the inefficiency of writes in STT-MRAM, we propose to reduce write voltage and duration. To evaluate the ensuing accuracy-efficiency trade-off, we conduct a thorough analysis of the error tolerance of input activations, weights, and errors during the training. We propose heterogeneous memory configurations that enable training convergence with good accuracy. We show that MRAM provide up to 15-22x improvement in system level energy across a suite of DNN benchmarks under iso-capacity and iso-area scenarios. Further optimizing STT-MRAM write operations can provide over 2x improvement in write energy for minimal degradation in application-level training accuracy.

cs.AR↗
arXiv2023

Verifiable Goal Recognition for Autonomous Driving with Occlusions

Goal recognition (GR) involves inferring the goals of other vehicles, such as a certain junction exit, which can enable more accurate prediction of their future behaviour. In autonomous driving, vehicles can encounter many different scenarios and the environment may be partially observable due to occlusions. We present a novel GR method named Goal Recognition with Interpretable Trees under Occlusion (OGRIT). OGRIT uses decision trees learned from vehicle trajectory data to infer the probabilities of a set of generated goals. We demonstrate that OGRIT can handle missing data due to occlusions and make inferences across multiple scenarios using the same learned decision trees, while being computationally fast, accurate, interpretable and verifiable. We also release the inDO, rounDO and OpenDDO datasets of occluded regions used to evaluate OGRIT.

cs.RO↗
arXiv2023

Unveiling the origins of quasi-phase matching spectral imperfections in thin-film lithium niobate frequency doublers

Thin-film lithium niobate (TFLN) based frequency doublers have been widely recognized as essential components for both classical and quantum optical communications. Nonetheless, the efficiency of these devices is hindered by imperfections present in the quasi-phase matching (QPM) spectrum. In this study, we present a thorough analysis of the spectral imperfections in TFLN frequency doublers with varying lengths, ranging from 5 mm to 15 mm. Employing a non-destructive diagnostic method based on scattered light imaging, we identify the sources and waveguide sections that contribute to the imperfections in the QPM spectrum. Furthermore, by mapping the TFLN film thickness across the entire waveguiding regions, we successfully reproduce the QPM spectra numerically, thus confirming the prominent influence of film thickness variations on the observed spectral imperfections. This comprehensive investigation provides valuable insights into the identification and mitigation of spectral imperfections in TFLN-based frequency doublers, paving the way toward the realization of nonlinear optical devices with enhanced efficiency and improved spectral fidelity.

physics.optics↗
arXiv2023

Freezing transition in particle-conserving East model

Quantum kinetically constrained models can exhibit a wealth of dynamical phenomena ranging from anomalous transport to Hilbert-space fragmentation (HSF). We study a class of one-dimensional particle number conserving systems where particle hoppings are subjected to an East-like constraint, akin to facilitated spin models in classical glasses. While such a kinetic constraint leads to HSF, we find that the degree of fragmentation exhibits a sharp transition as the average particle density is varied. Below a critical density, the system transitions from being weakly fragmented where most of the initial states thermalize diffusively, to strongly fragmented where the dynamics are frozen and the system fails to thermalize. Remarkably, the East model allows for both efficient numerical simulations and analytic solutions of various diagnostics of the phase transition, from which we obtain a set of exact critical exponents. We find that the freezing transition in particle-conserving East models belongs to the same universality class as dipole-conserving fracton systems. Our results provide a tractable minimal model for filling-induced freezing transitions associated with HSF, which can be readily tested in state-of-the-art quantum platforms.

cond-mat.stat-mech↗
arXiv2023

Ground-state cooling of a mechanical oscillator by heating

Dissipation and the accompanying fluctuations are often seen as detrimental for quantum systems, since they are associated with fast relaxation and loss of phase coherence. However, it has been proposed that a pure state can be prepared if external noise induces suitable downwards transitions, while exciting transitions are blocked. We demonstrate such a refrigeration mechanism in a cavity optomechanical system, where we prepare a mechanical oscillator in its ground state by injecting strong electromagnetic noise at frequencies around the red mechanical sideband of the cavity. The optimum cooling is reached with a noise bandwidth smaller than, but on the order of the cavity decay rate. At higher bandwidths, cooling is less efficient. In the opposite regime where the noise bandwidth becomes comparable to the mechanical damping rate, damping follows the noise amplitude adiabatically, and the cooling is also suppressed.

quant-ph↗
arXiv2023

To be or not to be polar: the ferroelectric and antiferroelectric nematic phases

We report the properties of two new series of compounds that show the ferroelectric nematic phase in which the length of a terminal chain is varied. The longer the terminal chain, the weaker the dipole-dipole interactions of the molecules are along the director, and thus the lower the temperature at which the axially ferroelectric nematic phase is formed. For homologues of intermediate chain length, between the non-polar and ferroelectric nematic phases, there is a wide temperature range nematic phase with antiferroelectric character. The size of the antiparallel ferroelectric domains critically increases upon transition to the ferroelectric phase. In dielectric studies, both collective ("ferroelectric" and non-collective fluctuations are present, the "ferroelectric" mode softens weakly at the N-NX phase transition because the polar order in this phase is weak. The transition to the NF phase is characterized by a much stronger lowering of the mode relaxation frequency and an increase in its strength, typical critical behavior is observed.

cond-mat.soft↗
arXiv2023

FLGo: A Fully Customizable Federated Learning Platform

Federated learning (FL) has found numerous applications in healthcare, finance, and IoT scenarios. Many existing FL frameworks offer a range of benchmarks to evaluate the performance of FL under realistic conditions. However, the process of customizing simulations to accommodate application-specific settings, data heterogeneity, and system heterogeneity typically remains unnecessarily complicated. This creates significant hurdles for traditional ML researchers in exploring the usage of FL, while also compromising the shareability of codes across FL frameworks. To address this issue, we propose a novel lightweight FL platform called FLGo, to facilitate cross-application FL studies with a high degree of shareability. Our platform offers 40+ benchmarks, 20+ algorithms, and 2 system simulators as out-of-the-box plugins. We also provide user-friendly APIs for quickly customizing new plugins that can be readily shared and reused for improved reproducibility. Finally, we develop a range of experimental tools, including parallel acceleration, experiment tracker and analyzer, and parameters auto-tuning. FLGo is maintained at \url{flgo-xmu.github.io}.

cs.LG↗
arXiv2023

Spatio-Temporal Joint Graph Convolutional Networks for Traffic Forecasting

Recent studies have shifted their focus towards formulating traffic forecasting as a spatio-temporal graph modeling problem. Typically, they constructed a static spatial graph at each time step and then connected each node with itself between adjacent time steps to create a spatio-temporal graph. However, this approach failed to explicitly reflect the correlations between different nodes at different time steps, thus limiting the learning capability of graph neural networks. Additionally, those models overlooked the dynamic spatio-temporal correlations among nodes by using the same adjacency matrix across different time steps. To address these limitations, we propose a novel approach called Spatio-Temporal Joint Graph Convolutional Networks (STJGCN) for accurate traffic forecasting on road networks over multiple future time steps. Specifically, our method encompasses the construction of both pre-defined and adaptive spatio-temporal joint graphs (STJGs) between any two time steps, which represent comprehensive and dynamic spatio-temporal correlations. We further introduce dilated causal spatio-temporal joint graph convolution layers on the STJG to capture spatio-temporal dependencies from distinct perspectives with multiple ranges. To aggregate information from different ranges, we propose a multi-range attention mechanism. Finally, we evaluate our approach on five public traffic datasets and experimental results demonstrate that STJGCN is not only computationally efficient but also outperforms 11 state-of-the-art baseline methods.

cs.LG↗
arXiv2023

C2-CRS: Coarse-to-Fine Contrastive Learning for Conversational Recommender System

Conversational recommender systems (CRS) aim to recommend suitable items to users through natural language conversations. For developing effective CRSs, a major technical issue is how to accurately infer user preference from very limited conversation context. To address issue, a promising solution is to incorporate external data for enriching the context information. However, prior studies mainly focus on designing fusion models tailored for some specific type of external data, which is not general to model and utilize multi-type external data. To effectively leverage multi-type external data, we propose a novel coarse-to-fine contrastive learning framework to improve data semantic fusion for CRS. In our approach, we first extract and represent multi-grained semantic units from different data signals, and then align the associated multi-type semantic units in a coarse-to-fine way. To implement this framework, we design both coarse-grained and fine-grained procedures for modeling user preference, where the former focuses on more general, coarse-grained semantic fusion and the latter focuses on more specific, fine-grained semantic fusion. Such an approach can be extended to incorporate more kinds of external data. Extensive experiments on two public CRS datasets have demonstrated the effectiveness of our approach in both recommendation and conversation tasks.

cs.CL↗
arXiv2023

Scalable wavelength-multiplexing photonic reservoir computing

Photonic reservoir computing (PRC) is a special hardware recurrent neural network, which is featured with fast training speed and low training cost. This work shows a wavelength-multiplexing PRC architecture, taking advantage of the numerous longitudinal modes in a Fabry-Perot semiconductor laser. These modes construct connected physical neurons in parallel, while an optical feedback loop provides interactive virtual neurons in series. We experimentally demonstrate a four-channel wavelength-multiplexing PRC, which runs four times faster than the single-channel case. It is proved that the multiplexing PRC exhibits superior performance on the task of signal equalization in an optical fiber communication link. Particularly, this scheme is highly scalable owing to the rich mode resources in Fabry-Perot lasers.

physics.optics↗
arXiv2023

Optimizing Energy Efficiency in Metro Systems Under Uncertainty Disturbances Using Reinforcement Learning

In the realm of urban transportation, metro systems serve as crucial and sustainable means of public transit. However, their substantial energy consumption poses a challenge to the goal of sustainability. Disturbances such as delays and passenger flow changes can further exacerbate this issue by negatively affecting energy efficiency in metro systems. To tackle this problem, we propose a policy-based reinforcement learning approach that reschedules the metro timetable and optimizes energy efficiency in metro systems under disturbances by adjusting the dwell time and cruise speed of trains. Our experiments conducted in a simulation environment demonstrate the superiority of our method over baseline methods, achieving a traction energy consumption reduction of up to 10.9% and an increase in regenerative braking energy utilization of up to 47.9%. This study provides an effective solution to the energy-saving problem of urban rail transit.

cs.AI↗