arXiv subjects

Kui Wu

Publications and source records attributed to Kui Wu.

At least 73 records · Page 4Linked to original sources

arXiv2021

Detecting and Identifying Optical Signal Attacks on Autonomous Driving Systems

For autonomous driving, an essential task is to detect surrounding objects accurately. To this end, most existing systems use optical devices, including cameras and light detection and ranging (LiDAR) sensors, to collect environment data in real time. In recent years, many researchers have developed advanced machine learning models to detect surrounding objects. Nevertheless, the aforementioned optical devices are vulnerable to optical signal attacks, which could compromise the accuracy of object detection. To address this critical issue, we propose a framework to detect and identify sensors that are under attack. Specifically, we first develop a new technique to detect attacks on a system that consists of three sensors. Our main idea is to: 1) use data from three sensors to obtain two versions of depth maps (i.e., disparity) and 2) detect attacks by analyzing the distribution of disparity errors. In our study, we use real data sets and the state-of-the-art machine learning model to evaluate our attack detection scheme and the results confirm the effectiveness of our detection method. Based on the detection scheme, we further develop an identification model that is capable of identifying up to n-2 attacked sensors in a system with one LiDAR and n cameras. We prove the correctness of our identification scheme and conduct experiments to show the accuracy of our identification method. Finally, we investigate the overall sensitivity of our framework.

cs.CV↗

arXiv2021

Prepartition: Load Balancing Approach for Virtual Machine Reservations in a Cloud Data Center

Load balancing is vital for the efficient and long-term operation of cloud data centers. With virtualization, post (reactive) migration of virtual machines after allocation is the traditional way for load balancing and consolidation. However, reactive migration is not easy to obtain predefined load balance objectives and may interrupt services and bring instability. Therefore, we provide a new approach, called Prepartition, for load balancing. It partitions a VM request into a few sub-requests sequentially with start time, end time and capacity demands, and treats each sub-request as a regular VM request. In this way, it can proactively set a bound for each VM request on each physical machine and makes the scheduler get ready before VM migration to obtain the predefined load balancing goal, which supports the resource allocation in a fine-grained manner. Simulations with real-world trace and synthetic data show that Prepartition for offline (PrepartitionOff) scheduling has 10%-20% better performance than the existing load balancing algorithms under several metrics, including average utilization, imbalance degree, makespan and Capacity_makespan. We also extend Prepartition to online load balancing. Evaluation results show that our proposed approach also outperforms existing online algorithms.

cs.DC↗

arXiv2021

DiffPD: Differentiable Projective Dynamics

We present a novel, fast differentiable simulator for soft-body learning and control applications. Existing differentiable soft-body simulators can be classified into two categories based on their time integration methods: Simulators using explicit time-stepping schemes require tiny time steps to avoid numerical instabilities in gradient computation, and simulators using implicit time integration typically compute gradients by employing the adjoint method and solving the expensive linearized dynamics. Inspired by Projective Dynamics (PD), we present Differentiable Projective Dynamics (DiffPD), an efficient differentiable soft-body simulator based on PD with implicit time integration. The key idea in DiffPD is to speed up backpropagation by exploiting the prefactorized Cholesky decomposition in forward PD simulation. In terms of contact handling, DiffPD supports two types of contacts: a penalty-based model describing contact and friction forces and a complementarity-based model enforcing non-penetration conditions and static friction. We evaluate the performance of DiffPD and observe it is 4-19 times faster compared with the standard Newton's method in various applications including system identification, inverse design problems, trajectory optimization, and closed-loop control. We also apply DiffPD in a reality-to-simulation (real-to-sim) example with contact and collisions and show its capability of reconstructing a digital twin of real-world scenes.

cs.LG↗

arXiv2021

BESS Aided Reconfigurable Energy Supply using Deep Reinforcement Learning for 5G and Beyond

The year of 2020 has witnessed the unprecedented development of 5G networks, along with the widespread deployment of 5G base stations (BSs). Nevertheless, the enormous energy consumption of BSs and the incurred huge energy cost have become significant concerns for the mobile operators. As the continuous decline of the renewable energy cost, equipping the power-hungry BSs with renewable energy generators could be a sustainable solution. In this work, we propose an energy storage aided reconfigurable renewable energy supply solution for the BS, which could supply clean energy to the BS and store surplus energy for backup usage. Specifically, to flexibly reconfigure the battery's discharging/charging operations, we propose a deep reinforcement learning based reconfiguring policy, which can adapt to the dynamical renewable energy generations as well as the varying power demands. Our experiments using the real-world data on renewable energy generations and power demands demonstrate that, our reconfigurable power supply solution can achieve an energy saving ratio of 74.8%, compared to the case with traditional power grid supply.

cs.DC↗

arXiv2021

On the Difficulty of Generalizing Reinforcement Learning Framework for Combinatorial Optimization

Combinatorial optimization problems (COPs) on the graph with real-life applications are canonical challenges in Computer Science. The difficulty of finding quality labels for problem instances holds back leveraging supervised learning across combinatorial problems. Reinforcement learning (RL) algorithms have recently been adopted to solve this challenge automatically. The underlying principle of this approach is to deploy a graph neural network (GNN) for encoding both the local information of the nodes and the graph-structured data in order to capture the current state of the environment. Then, it is followed by the actor to learn the problem-specific heuristics on its own and make an informed decision at each state for finally reaching a good solution. Recent studies on this subject mainly focus on a family of combinatorial problems on the graph, such as the travel salesman problem, where the proposed model aims to find an ordering of vertices that optimizes a given objective function. We use the security-aware phone clone allocation in the cloud as a classical quadratic assignment problem (QAP) to investigate whether or not deep RL-based model is generally applicable to solve other classes of such hard problems. Extensive empirical evaluation shows that existing RL-based model may not generalize to QAP.

cs.LG↗

arXiv2021

Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous Vehicles

In recent years, many deep learning models have been adopted in autonomous driving. At the same time, these models introduce new vulnerabilities that may compromise the safety of autonomous vehicles. Specifically, recent studies have demonstrated that adversarial attacks can cause a significant decline in detection precision of deep learning-based 3D object detection models. Although driving safety is the ultimate concern for autonomous driving, there is no comprehensive study on the linkage between the performance of deep learning models and the driving safety of autonomous vehicles under adversarial attacks. In this paper, we investigate the impact of two primary types of adversarial attacks, perturbation attacks and patch attacks, on the driving safety of vision-based autonomous vehicles rather than the detection precision of deep learning models. In particular, we consider two state-of-the-art models in vision-based 3D object detection, Stereo R-CNN and DSGN. To evaluate driving safety, we propose an end-to-end evaluation framework with a set of driving safety performance metrics. By analyzing the results of our extensive evaluation experiments, we find that (1) the attack's impact on the driving safety of autonomous vehicles and the attack's impact on the precision of 3D object detectors are decoupled, and (2) the DSGN model demonstrates stronger robustness to adversarial attacks than the Stereo R-CNN model. In addition, we further investigate the causes behind the two findings with an ablation study. The findings of this paper provide a new perspective to evaluate adversarial attacks and guide the selection of deep learning models in autonomous driving.

cs.CV↗

arXiv2021

DiffAqua: A Differentiable Computational Design Pipeline for Soft Underwater Swimmers with Shape Interpolation

The computational design of soft underwater swimmers is challenging because of the high degrees of freedom in soft-body modeling. In this paper, we present a differentiable pipeline for co-designing a soft swimmer's geometry and controller. Our pipeline unlocks gradient-based algorithms for discovering novel swimmer designs more efficiently than traditional gradient-free solutions. We propose Wasserstein barycenters as a basis for the geometric design of soft underwater swimmers since it is differentiable and can naturally interpolate between bio-inspired base shapes via optimal transport. By combining this design space with differentiable simulation and control, we can efficiently optimize a soft underwater swimmer's performance with fewer simulations than baseline methods. We demonstrate the efficacy of our method on various design problems such as fast, stable, and energy-efficient swimming and demonstrate applicability to multi-objective design.

cs.LG↗

arXiv2021

Addressing the Vulnerability of NMT in Input Perturbations

Neural Machine Translation (NMT) has achieved significant breakthrough in performance but is known to suffer vulnerability to input perturbations. As real input noise is difficult to predict during training, robustness is a big issue for system deployment. In this paper, we improve the robustness of NMT models by reducing the effect of noisy words through a Context-Enhanced Reconstruction (CER) approach. CER trains the model to resist noise in two steps: (1) perturbation step that breaks the naturalness of input sequence with made-up words; (2) reconstruction step that defends the noise propagation by generating better and more robust contextual representation. Experimental results on Chinese-English (ZH-EN) and French-English (FR-EN) translation tasks demonstrate robustness improvement on both news and social media text. Further fine-tuning experiments on social media text show our approach can converge at a higher position and provide a better adaptation.

cs.CL↗

arXiv2020

A Learning-based Discretionary Lane-Change Decision-Making Model with Driving Style Awareness

Discretionary lane change (DLC) is a basic but complex maneuver in driving, which aims at reaching a faster speed or better driving conditions, e.g., further line of sight or better ride quality. Although many DLC decision-making models have been studied in traffic engineering and autonomous driving, the impact of human factors, which is an integral part of current and future traffic flow, is largely ignored in the existing literature. In autonomous driving, the ignorance of human factors of surrounding vehicles will lead to poor interaction between the ego vehicle and the surrounding vehicles, thus, a high risk of accidents. The human factors are also a crucial part to simulate a human-like traffic flow in the traffic engineering area. In this paper, we integrate the human factors that are represented by driving styles to design a new DLC decision-making model. Specifically, our proposed model takes not only the contextual traffic information but also the driving styles of surrounding vehicles into consideration and makes lane-change/keep decisions. Moreover, the model can imitate human drivers' decision-making maneuvers to the greatest extent by learning the driving style of the ego vehicle. Our evaluation results show that the proposed model almost follows the human decision-making maneuvers, which can achieve 98.66% prediction accuracy with respect to human drivers' decisions against the ground truth. Besides, the lane-change impact analysis results demonstrate that our model even performs better than human drivers in terms of improving the safety and speed of traffic.

cs.RO↗

arXiv2020

PLVER: Joint Stable Allocation and Content Replication for Edge-assisted Live Video Delivery

The live streaming services have gained extreme popularity in recent years. Due to the spiky traffic patterns of live videos, utilizing the distributed edge servers to improve viewers' quality of experience (QoE) has become a common practice nowadays. Nevertheless, current client-driven content caching mechanism does not support caching beforehand from the cloud to the edge, resulting in considerable cache missing in live video delivery. State-of-the-art research generally sacrifices the liveness of delivered videos in order to deal with the above problem. In this paper, by jointly considering the features of live videos and edge servers, we propose PLVER, a proactive live video push scheme to resolve the cache miss problem in live video delivery. Specifically, PLVER first conducts a one-tomultiple stable allocation between edge clusters and user groups, to balance the load of live traffic over the edge servers. Then it adopts proactive video replication algorithms to speed up the video replication among the edge servers. We conduct extensive trace-driven evaluations, covering 0.3 million Twitch viewers and more than 300 Twitch channels. The results demonstrate that with PLVER, edge servers can carry 28% and 82% more traffic than the auction-based replication method and the caching on requested time method, respectively.

cs.NI↗

arXiv2020

Quantifying Low-Battery Anxiety of Mobile Users and Its Impacts on Video Watching Behavior

People nowadays are increasingly dependent on mobile phones for daily communication, study, and business. Along with this it incurs the low-battery anxiety (LBA). Although having been unveiled for a while, LBA has not been thoroughly investigated yet. Without a better understanding of LBA, it would be difficult to precisely validate energy saving and management techniques in terms of alleviating LBA and enhancing Quality of Experience (QoE) of mobile users. To fill the gap, we conduct an investigation over 2000+ mobile users, look into their feelings and reactions towards LBA, and quantify their anxiety degree during the draining of battery power. As a case study, we also investigate the impact of LBA on user's behavior at video watching, and with the massive collected answers we are able to quantify user's abandoning likelihood of attractive videos versus the battery status of mobile phone. The empirical findings and quantitative models obtained in this work not only disclose the characteristics of LBA among modern mobile users, but also provide valuable references for the design, evaluation, and improvement of QoE-aware mobile applications and services.

cs.HC↗

arXiv2014

Buyer to Seller Recommendation under Constraints

The majority of recommender systems are designed to recommend items (such as movies and products) to users. We focus on the problem of recommending buyers to sellers which comes with new challenges: (1) constraints on the number of recommendations buyers are part of before they become overwhelmed, (2) constraints on the number of recommendations sellers receive within their budget, and (3) constraints on the set of buyers that sellers want to receive (e.g., no more than two people from the same household). We propose the following critical problems of recommending buyers to sellers: Constrained Recommendation (C-REC) capturing the first two challenges, and Conflict-Aware Constrained Recommendation (CAC-REC) capturing all three challenges at the same time. We show that C-REC can be modeled using linear programming and can be efficiently solved using modern solvers. On the other hand, we show that CAC-REC is NP-hard. We propose two approximate algorithms to solve CAC-REC and show that they achieve close to optimal solutions via comprehensive experiments using real-world datasets.

cs.SI↗

arXiv2014

Household Electricity Consumption Data Cleansing

Load curve data in power systems refers to users' electrical energy consumption data periodically collected with meters. It has become one of the most important assets for modern power systems. Many operational decisions are made based on the information discovered in the data. Load curve data, however, usually suffers from corruptions caused by various factors, such as data transmission errors or malfunctioning meters. To solve the problem, tremendous research efforts have been made on load curve data cleansing. Most existing approaches apply outlier detection methods from the supply side (i.e., electricity service providers), which may only have aggregated load data. In this paper, we propose to seek aid from the demand side (i.e., electricity service users). With the help of readily available knowledge on consumers' appliances, we present a new appliance-driven approach to load curve data cleansing. This approach utilizes data generation rules and a Sequential Local Optimization Algorithm (SLOA) to solve the Corrupted Data Identification Problem (CDIP). We evaluate the performance of SLOA with real-world trace data and synthetic data. The results indicate that, comparing to existing load data cleansing methods, such as B-spline smoothing, our approach has an overall better performance and can effectively identify consecutive corrupted data. Experimental results also demonstrate that our method is robust in various tests. Our method provides a highly feasible and reliable solution to an emerging industry application.

cs.CE↗

arXiv2014

From Landscape to Portrait: A New Approach for Outlier Detection in Load Curve Data

In power systems, load curve data is one of the most important datasets that are collected and retained by utilities. The quality of load curve data, however, is hard to guarantee since the data is subject to communication losses, meter malfunctions, and many other impacts. In this paper, a new approach to analyzing load curve data is presented. The method adopts a new view, termed \textit{portrait}, on the load curve data by analyzing the periodic patterns in the data and re-organizing the data for ease of analysis. Furthermore, we introduce algorithms to build the virtual portrait load curve data, and demonstrate its application on load curve data cleansing. Compared to existing regression-based methods, our method is much faster and more accurate for both small-scale and large-scale real-world datasets.

cs.DC↗

arXiv2014

Plug and Play! A Simple, Universal Model for Energy Disaggregation

Energy disaggregation is to discover the energy consumption of individual appliances from their aggregated energy values. To solve the problem, most existing approaches rely on either appliances' signatures or their state transition patterns, both hard to obtain in practice. Aiming at developing a simple, universal model that works without depending on sophisticated machine learning techniques or auxiliary equipments, we make use of easily accessible knowledge of appliances and the sparsity of the switching events to design a Sparse Switching Event Recovering (SSER) method. By minimizing the total variation (TV) of the (sparse) event matrix, SSER can effectively recover the individual energy consumption values from the aggregated ones. To speed up the process, a Parallel Local Optimization Algorithm (PLOA) is proposed to solve the problem in active epochs of appliance activities in parallel. Using real-world trace data, we compare the performance of our method with that of the state-of-the-art solutions, including Least Square Estimation (LSE) and iterative Hidden Markov Model (HMM). The results show that our approach has an overall higher detection accuracy and a smaller overhead.

cs.AI↗

arXiv2014

Taking A Free Ride for Routing Topology Inference in Peer-to-Peer Networks

A Peer-to-Peer (P2P) network can boost its performance if peers are provided with underlying network-layer routing topology. The task of inferring the network-layer routing topology and link performance from an end host to a set of other hosts is termed as network tomography, and it normally requires host computers to send probing messages. We design a passive network tomography method that does not requires any probing messages and takes a free ride over data flows in P2P networks. It infers routing topology based on end-to-end delay correlation estimation (DCE) without requiring any synchronization or cooperation from the intermediate routers. We implement and test our method in the real world Internet environment and achieved the accuracy of 92% in topology recovery. We also perform extensive simulation in OMNet++ to evaluate its performance over large scale networks, showing that its topology recovery accuracy is about 95% for large networks.

cs.NI↗

arXiv2014

A Survey on Network Tomography with Network Coding

The overhead of internal network monitoring motivates techniques of network tomography. Network coding (NC) presents a new opportunity for network tomography as NC introduces topology-dependent correlation that can be further exploited in topology estimation. Compared with traditional methods, network tomography with NC has many advantages such as the improvement of tomography accuracy and the reduction of complexity in choosing monitoring paths. In this paper we first introduce the problem of tomography with NC and then propose the taxonomy criteria to classify various methods. We also present existing solutions and future trend. We expect that our comprehensive review on network tomography with NC can serve as a good reference for researchers and practitioners working in the area.

cs.NI↗

arXiv2013

DCE: A Novel Delay Correlation Measurement for Tomography with Passive Realization

Tomography is important for network design and routing optimization. Prior approaches require either precise time synchronization or complex cooperation. Furthermore, active tomography consumes explicit probeing resulting in limited scalability. To address the first issue we propose a novel Delay Correlation Estimation methodology named DCE with no need of synchronization and special cooperation. For the second issue we develop a passive realization mechanism merely using regular data flow without explicit bandwidth consumption. Extensive simulations in OMNeT++ are made to evaluate its accuracy where we show that DCE measured delay correlation is highly identical with the true value. Also from test result we find that mechanism of passive realization is able to achieve both regular data transmission and purpose of tomography with excellent robustness versus different background traffic and package size.

cs.NI↗