Searcharxiv⌕ Search

arXiv subjects

Kai Zeng

Publications and source records attributed to Kai Zeng.

At least 55 records · Page 3Linked to original sources
arXiv2021

A Unified Transferable Model for ML-Enhanced DBMS

Recently, the database management system (DBMS) community has witnessed the power of machine learning (ML) solutions for DBMS tasks. Despite their promising performance, these existing solutions can hardly be considered satisfactory. First, these ML-based methods in DBMS are not effective enough because they are optimized on each specific task, and cannot explore or understand the intrinsic connections between tasks. Second, the training process has serious limitations that hinder their practicality, because they need to retrain the entire model from scratch for a new DB. Moreover, for each retraining, they require an excessive amount of training data, which is very expensive to acquire and unavailable for a new DB. We propose to explore the transferabilities of the ML methods both across tasks and across DBs to tackle these fundamental drawbacks. In this paper, we propose a unified model MTMLF that uses a multi-task training procedure to capture the transferable knowledge across tasks and a pre-train fine-tune procedure to distill the transferable meta knowledge across DBs. We believe this paradigm is more suitable for cloud DB service, and has the potential to revolutionize the way how ML is used in DBMS. Furthermore, to demonstrate the predicting power and viability of MTMLF, we provide a concrete and very promising case study on query optimization tasks. Last but not least, we discuss several concrete research opportunities along this line of work.

cs.DB↗
arXiv2021

Improving Dither Modulation based Robust Steganography by Overflow Suppression

Nowadays, people are sharing their pictures on online social networks (OSNs), so OSN is a good platform for Steganography. But OSNs usually perform JPEG compression on the uploaded image, which will invalidate most of the existing steganography algorithms. Recently, some works try to design robust steganography which can resist JPEG compression, such as Dither Modulation-based robust Adaptive Steganography (DMAS) and Generalized dither Modulation-based robust Adaptive Steganography (GMAS). They relieve the problem that the receivers cannot extract the message correctly when the quality factor of channel JPEG compression is larger than that of cover images. However, they only can realize limited resistance to detection and compression due to robust domain selection. To overcome this problem, we meticulously explore three lossy operations in the JPEG recompression and discover that the key problem is spatial overflow. Then two preprocessing methods Overall Scaling (OS) and Specific Truncation (ST) are presented to remove overflow before message embedding as well as generate a reference image. The reference image is employed as the guidance to build asymmetric distortion for removing overflow during embedding. Experimental results show that the proposed methods significantly surpass GMAS in terms of security and achieve comparable robustness.

cs.CR↗
arXiv2021

Cardinality Estimation in DBMS: A Comprehensive Benchmark Evaluation

Cardinality estimation (CardEst) plays a significant role in generating high-quality query plans for a query optimizer in DBMS. In the last decade, an increasing number of advanced CardEst methods (especially ML-based) have been proposed with outstanding estimation accuracy and inference latency. However, there exists no study that systematically evaluates the quality of these methods and answer the fundamental problem: to what extent can these methods improve the performance of query optimizer in real-world settings, which is the ultimate goal of a CardEst method. In this paper, we comprehensively and systematically compare the effectiveness of CardEst methods in a real DBMS. We establish a new benchmark for CardEst, which contains a new complex real-world dataset STATS and a diverse query workload STATS-CEB. We integrate multiple most representative CardEst methods into an open-source database system PostgreSQL, and comprehensively evaluate their true effectiveness in improving query plan quality, and other important aspects affecting their applicability, ranging from inference latency, model size, and training time, to update efficiency and accuracy. We obtain a number of key findings for the CardEst methods, under different data and query settings. Furthermore, we find that the widely used estimation accuracy metric(Q-Error) cannot distinguish the importance of different sub-plan queries during query optimization and thus cannot truly reflect the query plan quality generated by CardEst methods. Therefore, we propose a new metric P-Error to evaluate the performance of CardEst methods, which overcomes the limitation of Q-Error and is able to reflect the overall end-to-end performance of CardEst methods. We have made all of the benchmark data and evaluation code publicly available at https://github.com/Nathaniel-Han/End-to-End-CardEst-Benchmark.

cs.DB↗
arXiv2021

FLAT: Fast, Lightweight and Accurate Method for Cardinality Estimation

Query optimizers rely on accurate cardinality estimation (CardEst) to produce good execution plans. The core problem of CardEst is how to model the rich joint distribution of attributes in an accurate and compact manner. Despite decades of research, existing methods either over simplify the models only using independent factorization which leads to inaccurate estimates, or over complicate them by lossless conditional factorization without any independent assumption which results in slow probability computation. In this paper, we propose FLAT, a CardEst method that is simultaneously fast in probability computation, lightweight in model size and accurate in estimation quality. The key idea of FLAT is a novel unsupervised graphical model, called FSPN. It utilizes both independent and conditional factorization to adaptively model different levels of attributes correlations, and thus dovetails their advantages. FLAT supports efficient online probability computation in near liner time on the underlying FSPN model, provides effective offline model construction and enables incremental model updates. It can estimate cardinality for both single table queries and multi table join queries. Extensive experimental study demonstrates the superiority of FLAT over existing CardEst methods on well known IMDB benchmarks: FLAT achieves 1 to 5 orders of magnitude better accuracy, 1 to 3 orders of magnitude faster probability computation speed and 1 to 2 orders of magnitude lower storage cost. We also integrate FLAT into Postgres to perform an end to end test. It improves the query execution time by 12.9% on the benchmark workload, which is very close to the optimal result 14.2% using the true cardinality.

cs.DB↗
arXiv2021

MicroRec: Efficient Recommendation Inference by Hardware and Data Structure Solutions

Deep neural networks are widely used in personalized recommendation systems. Unlike regular DNN inference workloads, recommendation inference is memory-bound due to the many random memory accesses needed to lookup the embedding tables. The inference is also heavily constrained in terms of latency because producing a recommendation for a user must be done in about tens of milliseconds. In this paper, we propose MicroRec, a high-performance inference engine for recommendation systems. MicroRec accelerates recommendation inference by (1) redesigning the data structures involved in the embeddings to reduce the number of lookups needed and (2) taking advantage of the availability of High-Bandwidth Memory (HBM) in FPGA accelerators to tackle the latency by enabling parallel lookups. We have implemented the resulting design on an FPGA board including the embedding lookup step as well as the complete inference process. Compared to the optimized CPU baseline (16 vCPU, AVX2-enabled), MicroRec achieves 13.8~14.7x speedup on embedding lookup alone and 2.5$~5.4x speedup for the entire recommendation inference in terms of throughput. As for latency, CPU-based engines needs milliseconds for inferring a recommendation while MicroRec only takes microseconds, a significant advantage in real-time recommendation systems.

cs.AR↗
arXiv2021

BayesCard: Revitilizing Bayesian Frameworks for Cardinality Estimation

Cardinality estimation (CardEst) is an essential component in query optimizers and a fundamental problem in DBMS. A desired CardEst method should attain good algorithm performance, be stable to varied data settings, and be friendly to system deployment. However, no existing CardEst method can fulfill the three criteria at the same time. Traditional methods often have significant algorithm drawbacks such as large estimation errors. Recently proposed deep learning based methods largely improve the estimation accuracy but their performance can be greatly affected by data and often difficult for system deployment. In this paper, we revitalize the Bayesian networks (BN) for CardEst by incorporating the techniques of probabilistic programming languages. We present BayesCard, the first framework that inherits the advantages of BNs, i.e., high estimation accuracy and interpretability, while overcomes their drawbacks, i.e. low structure learning and inference efficiency. This makes BayesCard a perfect candidate for commercial DBMS deployment. Our experimental results on several single-table and multi-table benchmarks indicate BayesCard's superiority over existing state-of-the-art CardEst methods: BayesCard achieves comparable or better accuracy, 1-2 orders of magnitude faster inference time, 1-3 orders faster training time, 1-3 orders smaller model size, and 1-2 orders faster updates. Meanwhile, BayesCard keeps stable performance when varying data with different settings. We also deploy BayesCard into PostgreSQL. On the IMDB benchmark workload, it improves the end-to-end query time by 13.3%, which is very close to the optimal result of 14.2% using an oracle of true cardinality.

cs.DB↗
arXiv2021

REPOSE: Distributed Top-k Trajectory Similarity Search with Local Reference Point Tries

Trajectory similarity computation is a fundamental component in a variety of real-world applications, such as ridesharing, road planning, and transportation optimization. Recent advances in mobile devices have enabled an unprecedented increase in the amount of available trajectory data such that efficient query processing can no longer be supported by a single machine. As a result, means of performing distributed in-memory trajectory similarity search are called for. However, existing distributed proposals suffer from either computing resource waste or are unable to support the range of similarity measures that are being used. We propose a distributed in-memory management framework called REPOSE for processing top-k trajectory similarity queries on Spark. We develop a reference point trie (RP-Trie) index to organize trajectory data for local search. In addition, we design a novel heterogeneous global partitioning strategy to eliminate load imbalance in distributed settings. We report on extensive experiments with real-world data that offer insight into the performance of the solution, and show that the solution is capable of outperforming the state-of-the-art proposals.

cs.DB↗
arXiv2021

A Pluggable Learned Index Method via Sampling and Gap Insertion

Database indexes facilitate data retrieval and benefit broad applications in real-world systems. Recently, a new family of index, named learned index, is proposed to learn hidden yet useful data distribution and incorporate such information into the learning of indexes, which leads to promising performance improvements. However, the "learning" process of learned indexes is still under-explored. In this paper, we propose a formal machine learning based framework to quantify the index learning objective, and study two general and pluggable techniques to enhance the learning efficiency and learning effectiveness for learned indexes. With the guidance of the formal learning objective, we can efficiently learn index by incorporating the proposed sampling technique, and learn precise index with enhanced generalization ability brought by the proposed result-driven gap insertion technique. We conduct extensive experiments on real-world datasets and compare several indexing methods from the perspective of the index learning objective. The results show the ability of the proposed framework to help to design suitable indexes for different scenarios. Further, we demonstrate the effectiveness of the proposed sampling technique, which achieves up to 78x construction speedup while maintaining non-degraded indexing performance. Finally, we show the gap insertion technique can enhance both the static and dynamic indexing performances of existing learned index methods with up to 1.59x query speedup. We will release our codes and processed data for further study, which can enable more exploration of learned indexes from both the perspectives of machine learning and database.

cs.DB↗
arXiv2020

FSPN: A New Class of Probabilistic Graphical Model

We introduce factorize sum split product networks (FSPNs), a new class of probabilistic graphical models (PGMs). FSPNs are designed to overcome the drawbacks of existing PGMs in terms of estimation accuracy and inference efficiency. Specifically, Bayesian networks (BNs) have low inference speed and performance of tree structured sum product networks(SPNs) significantly degrades in presence of highly correlated variables. FSPNs absorb their advantages by adaptively modeling the joint distribution of variables according to their dependence degree, so that one can simultaneously attain the two desirable goals: high estimation accuracy and fast inference speed. We present efficient probability inference and structure learning algorithms for FSPNs, along with a theoretical analysis and extensive evaluation evidence. Our experimental results on synthetic and benchmark datasets indicate the superiority of FSPN over other PGMs.

cs.AI↗
arXiv2020

Tempura: A General Cost Based Optimizer Framework for Incremental Data Processing (Extended Version)

Incremental processing is widely-adopted in many applications, ranging from incremental view maintenance, stream computing, to recently emerging progressive data warehouse and intermittent query processing. Despite many algorithms developed on this topic, none of them can produce an incremental plan that always achieves the best performance, since the optimal plan is data dependent. In this paper, we develop a novel cost-based optimizer framework, called Tempura, for optimizing incremental data processing. We propose an incremental query planning model called TIP based on the concept of time-varying relations, which can formally model incremental processing in its most general form. We give a full specification of Tempura, which can not only unify various existing techniques to generate an optimal incremental plan, but also allow the developer to add their rewrite rules. We study how to explore the plan space and search for an optimal incremental plan. We conduct a thorough experimental evaluation of Tempura in various incremental processing scenarios to show its effectiveness and efficiency.

cs.DB↗
arXiv2020

Consumer UAV Cybersecurity Vulnerability Assessment Using Fuzzing Tests

Unmanned Aerial Vehicles (UAVs) are remote-controlled vehicles capable of flight and are present in a variety of environments from military operations to domestic enjoyment. These vehicles are great assets, but just as their pilot can control them remotely, cyberattacks can be executed in a similar manner. Cyber attacks on UAVs can bring a plethora of issues to physical and virtual systems. Such malfunctions are capable of giving an attacker the ability to steal data, incapacitate the UAV, or hijack the UAV. To mitigate such attacks, it is necessary to identify and patch vulnerabilities that may be maliciously exploited. In this paper, a new UAV vulnerability is explored with related UAV security practices identified for possible exploitation using large streams of data sent at specific ports. The more in-depth model involves strings of data involving FTP-specific keywords sent to the UAV's FTP port in the form of a fuzzing test and launching thousands of packets at other ports on the UAV as well. During these tests, virtual and physical systems are monitored extensively to identify specific patterns and vulnerabilities. This model is applied to a Parrot Bebop 2, which accurately portrays a UAV that had their network compromised by an attacker and portrays many lower-end UAV models for domestic use. During testings, the Parrot Bebop 2 is monitored for degradation in GPS performance, video speed, the UAV's reactivity to the pilot, motor function, and the accuracy of the UAV's sensor data. All these points of monitoring give a comprehensive view of the UAV's reaction to each individual test. In this paper, countermeasures to combat the exploitation of this vulnerability will be discussed as well as possible attacks that can branch from the fuzzing tests.

cs.CR↗
arXiv2019

Machine Learning-Based Delay-Aware UAV Detection and Operation Mode Identification over Encrypted Wi-Fi Traffic

The consumer UAV (unmanned aerial vehicle) market has grown significantly over the past few years. Despite its huge potential in spurring economic growth by supporting various applications, the increase of consumer UAVs poses potential risks to public security and personal privacy. To minimize the risks, efficiently detecting and identifying invading UAVs is in urgent need for both invasion detection and forensics purposes. Given the fact that consumer UAVs are usually used in a civilian environment, existing physical detection methods (such as radar, vision, and sound) may become ineffective in many scenarios. Aiming to complement the existing physical detection mechanisms, we propose a machine learning-based framework for fast UAV identification over encrypted Wi-Fi traffic. It is motivated by the observation that many consumer UAVs use Wi-Fi links for control and video streaming. The proposed framework extracts features derived only from packet size and inter-arrival time of encrypted Wi-Fi traffic, and can efficiently detect UAVs and identify their operation modes. In order to reduce the online identification time, our framework adopts a re-weighted $\ell_1$-norm regularization, which considers the number of samples and computation cost of different features. This framework jointly optimizes feature selection and prediction performance in a unified objective function. To tackle the packet inter-arrival time uncertainty when optimizing the trade-off between the detection accuracy and delay, we utilize Maximum Likelihood Estimation (MLE) method to estimate the packet inter-arrival time. We collect a large number of real-world Wi-Fi data traffic of eight types of consumer UAVs and conduct extensive evaluation on the performance of our proposed method.

cs.CR↗
arXiv2019

Intelligent Policing Strategy for Traffic Violation Prevention

Police officer presence at an intersection discourages a potential traffic violator from violating the law. It also alerts the motorists' consciousness to take precaution and follow the rules. However, due to the abundant intersections and shortage of human resources, it is not possible to assign a police officer to every intersection. In this paper, we propose an intelligent and optimal policing strategy for traffic violation prevention. Our model consists of a specific number of targeted intersections and two police officers with no prior knowledge on the number of the traffic violations in the designated intersections. At each time interval, the proposed strategy, assigns the two police officers to different intersections such that at the end of the time horizon, maximum traffic violation prevention is achieved. Our proposed methodology adapts the PROLA (Play and Random Observe Learning Algorithm) algorithm [1] to achieve an optimal traffic violation prevention strategy. Finally, we conduct a case study to evaluate and demonstrate the performance of the proposed method.

cs.AI↗
arXiv2019

Physical Layer Key Generation in 5G Wireless Networks

The bloom of the fifth generation (5G) communication and beyond serves as a catalyst for physical layer key generation techniques. In 5G communications systems, many challenges in traditional physical layer key generation schemes, such as co-located eavesdroppers, the high bit disagreement ratio, and high temporal correlation, could be overcome. This paper lists the key-enabler techniques in 5G wireless networks, which offer opportunities to address existing issues in physical layer key generation. We survey the existing key generation methods and introduce possible solutions for the existing issues. The new solutions include applying the high signal directionality in beamforming to resist co-located eavesdroppers, utilizing the sparsity of millimeter wave (mmWave) channel to achieve a low bit disagreement ratio under low signal-to-noise-ratio (SNR), and exploiting hybrid precoding to reduce the temporal correlation among measured samples. Finally, the future trends of physical layer key generation in 5G and beyond communications are discussed.

eess.SP↗
arXiv2019

Multi-stage Deep Classifier Cascades for Open World Recognition

At present, object recognition studies are mostly conducted in a closed lab setting with classes in test phase typically in training phase. However, real-world problem is far more challenging because: i) new classes unseen in the training phase can appear when predicting; ii) discriminative features need to evolve when new classes emerge in real time; and iii) instances in new classes may not follow the "independent and identically distributed" (iid) assumption. Most existing work only aims to detect the unknown classes and is incapable of continuing to learn newer classes. Although a few methods consider both detecting and including new classes, all are based on the predefined handcrafted features that cannot evolve and are out-of-date for characterizing emerging classes. Thus, to address the above challenges, we propose a novel generic end-to-end framework consisting of a dynamic cascade of classifiers that incrementally learn their dynamic and inherent features. The proposed method injects dynamic elements into the system by detecting instances from unknown classes, while at the same time incrementally updating the model to include the new classes. The resulting cascade tree grows by adding a new leaf node classifier once a new class is detected, and the discriminative features are updated via an end-to-end learning strategy. Experiments on two real-world datasets demonstrate that our proposed method outperforms existing state-of-the-art methods.

cs.LG↗
arXiv2018

A Survey on Simulation Tools and Testbeds for Cognitive Radio Networks Study

Efficient utility of radio spectrum has been a hot topic as the wireless communication spectrum is a precious resource. The past decade has witnessed intensive research in spectrum sharing techniques. Most of the techniques are based on cognitive radio networks (CRNs) because cognitive capabilities are essential for optimizing spectrum efficiency and guaranteeing safe coexistence in the presence of the spectrum uncertainty. However, due to the high complexity of the problem, most research has been limited to theoretical analysis. It is non-trivial to build a simulator that is capable of carrying out a comprehensive experimental study. In this paper, a survey is conducted to provide a big picture of the available simulators in CRNs research. By illustrating their major functionalities, the insight enables researchers to select tools that match their needs. In addition, with a better understanding of the advantages and constraints, this survey aims at providing a guideline for simulator designers who have been trying to meet the requirements from the CRN research community.

cs.NI↗
arXiv2018

Explore Recurrent Neural Network for PUE Attack Detection in Practical CRN Models

The proliferation of the Internet of Things (IoTs) and pervasive use of many different types of mobile computing devices make wireless communication spectrum a precious resource. In order to accommodate the still fast increasing number of devices requesting wireless connection, more efficient, fine-grained spectrum allocation and sharing schemes are badly in need. Cognitive radio networks (CRNs) have been widely recognized as one promising solution, in which the secondary users (SUs) are allowed to share channels with licensed primary users (PUs) as long as bringing no interference to the normal operations of the PUs. However, malicious attackers or selfish SUs may mimic the behavior of PUs to occupy the channels illegally. It is nontrivial to accurately, timely detect such kind of primary user emulation (PUE) attacks. In this paper, an efficient PUE attacked detection method is introduced leveraging the recurrent neural network (RNN). After a fundamental algorithm using basic RNN, an advanced version taking advantage of long-short-term-memory (LSTM) is proposed, which is more efficient on processing time series with long term memory. The experimental study has provided deeper insights about the different performances the RNNs achieved and validated the effectiveness of the proposed detectors.

cs.NI↗