Cardinality estimation of LIKE predicate queries has an important role in the query optimization of database systems. Traditional approaches generally use a summary of text data with some statistical assumptions. Recently, the deep learning model for cardinality estimation of LIKE predicate queries has been investigated. To provide more accurate cardinality estimates and reduce the maximum estimation errors, we propose a deep learning model that utilizes the extended N-gram table and the conditional regression header. We next investigate how to efficiently generate training data. Our LEADER (LikE predicate trAining Data gEneRation) algorithms utilize the shareable results across the relational queries corresponding to the LIKE predicates. By analyzing the queries corresponding to LIKE predicates, we develop an efficient join method and utilize the join order for fast query execution and maximal sharing of shareable results. Extensive experiments with real-life datasets confirm the efficiency of the proposed training data generation algorithms and the effectiveness of the proposed model.

Geospatial data provides a lot of benefits for personalized services. However, since the geospatial data contains sensitive information about personal activities, collecting the raw data has a potential risk of leaking private information from the collectors. Recently, local differential privacy (LDP), which protects the privacy of users without trusting the collector, has been adopted to preserve privacy in many real applications. In this paper, we investigate the problem of collecting the locations of individual users under LDP, and propose a perturbation mechanism designed carefully to minimize the expected error of perturbed locations according to the privacy budget and the data domain. The frequency distribution of perturbed locations inevitably has a large error. To tackle the problem, we also propose a postprocessing algorithm to estimate the original frequency distribution of collected data by using convex optimization. By experiments with various real datasets, we show the effectiveness of the proposed algorithms.

Strong and weak supervisions have complementary characteristics. However, utilizing both supervisions for named entity recognition (NER) has not been extensively studied. Moreover, the existing works address only incomplete annotations and neglects inaccurate annotations during NER model training. To effectively utilize weak labels, we introduce an auxiliary classifier that learns from weak labels. Furthermore, we adopt the teacher-student framework to handle both incomplete and inaccurate weak labels. A teacher model is first trained using both strongly and weakly supervised data, and next generates pseudo labels to replace weak labels. Then, the student model is trained so that the main classifier learns from both strong labels and confident pseudo labels while the auxiliary classifier learns from less confident pseudo labels. We also incorporate data augmentation through ChatGPT to generate additional annotated sentences to improve model performance and generalization capabilities. The experimental results with different weak supervisions demonstrate that our proposed method surpasses existing techniques.

In recent years, large language models (LLMs) have garnered increasing attention from both academia and industry due to their potential to facilitate natural language processing (NLP) and generate highquality text. Despite their benefits, however, the use of LLMs is raising concerns about the reliability of knowledge extraction. The combination of DB research and data science has advanced the state of the art in solving real-world problems, such as merchandise recommendation and hazard prevention [30]. In this discussion, we explore the challenges and opportunities related to LLMs in DB and data science research and education.

최근 화두가 되고 있는 양자컴퓨팅 기술의 발전에 따라 기존의 통신 보안체계는 새로운 위협에 직면하고 있으며, 이에 따라 새로운 통신보안체계에 대한 이슈로 양자암호통신 기술이 부상하고 있으며, 양자암호통신은 양자키 분배, 데이터 암복호화, 데이터 전송기술로 구성되어 있다. 이 중 핵심이 되는 양자키 분배 기술은 양자의 불확정성의 원리를 활용하여 임의의 두 노드 사이에 대칭키를 기밀성을 보장하도록 생성 분배한다. 이에 따라, 최근 QKD 기반의 양자암호통신망 구축 및 서비스 응용 사례들이 등장하고 있다. 하지만 현재의 QKD 기반의 양자암호통신망 관리 및 서비스키 제공은 기본적인 기능 구현에 초점을 두고 있기 때문에 실질적인 양자암호통신 응용보안 서비스를 제공하기 위해서는 다양한 응용 서비스 요구사항을 고려한 양자키 관리 및 장애 대응 방안 등의 추가적인 연구가 필요하다. 이에 따라, 본 논문에서는 양자키 부족 현상을 해결하고 양자암호통신망에서 발생할 수 있는 장애에 대응하여 안정적인 양자암호통신망 서비스 환경을 마련하기 위한 양자키 확장 구조와 양자키 관리 정책에 대하여 제안한다. 또한 한정적인 양자키 자원을 활용하여 다양한 양자암호통신 서비스들의 요구사항에 따라 서비스키를 안정적이고 원활하게 제공하기 위한 서비스키 관리 방안에 대하여 제안하고자 한다.

Cardinality estimation of an approximate substring query is an important problem in database systems. Traditional approaches build a summary from the text data and estimate the cardinality using the summary with some statistical assumptions. Since deep learning models can learn underlying complex data patterns effectively, they have been successfully applied and shown to outperform traditional methods for cardinality estimations of queries in database systems. However, since they are not yet applied to approximate substring queries, we investigate a deep learning approach for cardinality estimation of such queries. Although the accuracy of deep learning models tends to improve as the train data size increases, producing a large train data is computationally expensive for cardinality estimation of approximate substring queries. Thus, we develop efficient train data generation algorithms by avoiding unnecessary computations and sharing common computations. We also propose a deep learning model as well as a novel learning method to quickly obtain an accurate deep learning-based estimator. Extensive experiments confirm the superiority of our data generation algorithms and deep learning model with the novel learning method.

An acronym is a word formed by abbreviating a phrase by combining certain letters of words in the phrase into a single term. Acronym disambiguation task selects the correct expansion of an ambiguous acronym in a sentence among the candidate expansions in a dictionary. Although it is convenient to use acronyms, identifying the appropriate expansions of an acronym in a sentence is a difficult task in natural language processing. Based on the recent success of the large-scale pre-trained language models such as BERT and T5, we propose a binary classification model using those language models for acronym disambiguation. To overcome the limited coverage of a training data, we use a weak supervision approach to increase the training data. Specifically, after collecting sentences containing an expansion of an acronym from Wikipedia, we replace the expansion with its acronym and label the sentence with the expansion. By conducting extensive experiments, we show the effectiveness of the proposed model. Our model is placed in the top 3 models for three of four categories in SDU@AAAI-22 shared task 2: Acronym Disambiguation.

Summary With the recent exponential increase in internet speeds, the traditional network environment is evolving into a high‐capacity network environment. Network traffic usage is also increasing exponentially, as are new malicious behaviors and related applications. Most of these applications and malicious behaviors use unknown protocols for which the structure is inaccessible; hence, protocol reverse engineering is receiving increasing attention in the field of network management. Various approaches have been proposed, but they still suffer from misidentification of field boundaries. To understand message structures properly, it is important to identify accurately the boundaries of the fields constituting the protocol message; accurate keyword extraction based on this approach leads to the correct inference of message types, semantics, and state machine. In this study, we propose a message keyword extraction method using accurate identification of field boundaries from delimiter inference and statistical analysis. Through the identification of field boundaries, messages can be subdivided into fields. We evaluate the efficacy of the proposed method by applying it to several textual and binary protocols. The proposed method showed better results than did other previous studies for both textual and binary protocols.

To allow deeper semantic understanding of strings, string matching with synonyms has recently received increasing attention. However, all the works focus on string semantics, which requires matching of entire strings, and cannot handle partial matching with substring semantics, resulting in its limited applications. To remedy this issue, we first propose a novel similarity measure between two strings allowing substring matching with synonyms, and develop an efficient algorithm to find the strings that have a substring semantically similar to the query string. Since considering synonyms on substrings enlarges the search space significantly, we devise efficient filtering methods to reduce the number of expensive similarity computations. Experiments with real-life datasets show the efficiency of our algorithm.

Geospatial data provides a lot of benefits for personalized services. However, since the geospatial data contains sensitive information about personal activities, collecting the raw data has a potential risk of leaking private information from the collectors. Recently, local differential privacy (LDP), which protects the privacy of users without trusting the collector, has been adopted to preserve privacy in many real applications. However, most of existing LDP algorithms focus on obtaining aggregated values such as mean and histogram from the collected data. In this paper, we investigate the problem of collecting the locations of individual users under LDP, and propose a perturbation mechanism designed carefully to reduce the error of each perturbed location according to the privacy budget and the domain size. In addition, we show the effectiveness of the proposed algorithm through experiments on various real datasets.

Log data from mobile devices generally contain a series of events with temporal information including time intervals which consist of the start and finish times. However, the problem of releasing differentially private time interval datasets has not been tackled yet. A time interval dataset can be represented by a two dimensional (2D) histogram. Most of the methods to publish 2D histograms partition the data into rectangular spaces to reduce the aggregated noise error for range queries. However, the existing algorithms to publish 2D histograms suffer from the structural error when applied to time interval datasets. To reduce the aggregated noise errors and suppress the increase in the structural error, we propose the TIDY (publishing Time Intervals via Differential privacY) algorithm. We use the frequency vectors as a compact representation of the time interval dataset. After applying the Laplace mechanism to the frequency vectors, we improve the utility of the frequency vectors based on a maximum likelihood estimation. We also develop a new partitioning method adapted for the frequency vectors to balance the trade-off between the noise and structural errors. Our empirical study on real-life and synthetic datasets confirms that TIDY outperforms the existing algorithms for 2D histograms.

SummaryAutomation in all aspects of industrial activity is currently needed in today's industries. Networks, which are the most essential elements of automation, have been widely used in industrial sites to realize such needs. However, network security threats and malfunctions at industrial sites can cause considerable physical damage. Damage can be prevented, and threats can be detected through network traffic monitoring. However, industrial protocols use self‐developed protocols to ensure rapid and efficient data transfer, and most self‐developed protocols are private networking protocols. Efficient network traffic monitoring requires a detailed understanding of the structure of industrial protocols. Studies on existing protocol reverse engineering methods for commercial protocols have indicated that there are many limitations in applying these methods to industrial protocols. Therefore, in this paper, we propose a method of analyzing the structure of private protocols that can be employed as industrial protocols. This methodology consists of six modules: traffic collection, message extraction, message clustering by size, message clustering by similarity, field extraction, and session analysis. We collect traffic using the Schneider Modicon M580 and demonstrate the validity of the proposed methodology by comparing collected traffic with existing protocol reverse engineering methods.

Relation extraction (RE) has been extensively studied due to its importance in real-world applications such as knowledge base construction and question answering. Most of the existing works train the models on either distantly supervised data or human-annotated data. To take advantage of the high accuracy of human annotation and the cheap cost of distant supervision, we propose the dual supervision framework which effectively utilizes both types of data. However, simply combining the two types of data to train a RE model may decrease the prediction accuracy since distant supervision has labeling bias. We employ two separate prediction networks HA-Net and DS-Net to predict the labels by human annotation and distant supervision, respectively, to prevent the degradation of accuracy by the incorrect labeling of distant supervision. Furthermore, we propose an additional loss term called disagreement penalty to enable HA-Net to learn from distantly supervised labels. In addition, we exploit additional networks to adaptively assess the labeling bias by considering contextual information. Our performance study on sentence-level and document-level REs confirms the effectiveness of the dual supervision framework.

최근 데이터에 대한 분석 결과로부터 개인 정보가 유출되는 것을 막기 위한 방법들이 연구되고 있다. 그중 차분 프라이버시(differential privacy)는 엄격하고 증명될 수 있는 개인 정보 보호를 보장하기 때문에 널리 연구되고 있는 개인 정보 보호의 표준이다. 본 논문에서는 2차원 데이터에 대하여 보로노이 다이어그램(Voronoi diagram)을 기반으로 차분 프라이버시를 보장하면서 K-평균 클러스터링 결과를 공개하기 위한 알고리즘을 제안한다. 기존 알고리즘은 클러스터링의 정확도와 수행 속도가 샘플 개수에 따라 변화하여 데이터에 적합한 샘플 개수를 선택하기 어렵다는 단점이 있으나 제안하는 알고리즘은 그러한 파라미터를 필요로 하지 않으면서 정확한 클러스터링 결과를 빠르게 계산할 수 있다. 제안하는 알고리즘의 성능에 대해 실생활 데이터를 이용한 실험을 통해 검증한다.

Protocol reverse engineering represents a very powerful and important tool for network management and security. To cope with the emergence and evolution of rapidly increasing numbers of unknown protocols, automation is of great importance. Many methods for supporting the automation of the various steps for protocol reverse engineering have been investigated; however, there has been no method to automate the analysis of the target network environment. Most methods are designed only for application layer protocols, and all others are designed for specific environments. Given any unknown communication, we must be able to infer the structure of the protocol. However, there has been no research on automatic reverse engineering of protocols when both the protocol and the target network environment are entirely unknown. Here, we propose an automatic protocol reverse engineering approach that is designed to be generally applicable, regardless of the specific network environment. We demonstrate the feasibility of the proposed approach by applying it to several protocols in various layers of the TCP/ IP reference model.

String matching is a fundamental operation in many applications such as data integration, information retrieval and text mining. Since users express the same meaning in a variety of ways that are not textually similar, existing works have proposed variants of Jaccard similarity by using synonyms to consider semantics beyond textual similarities. However, they may produce a non-negligible number of false positives in some applications by employing set semantics and miss some true positives due to approximations. In this paper, we define new match relationships between a pair of strings under synonym rules and develop an efficient algorithm to verify the match relationships for a pair of strings. In addition, we propose two filtering methods to prune non-matching string pairs. We also develop join algorithms with synonyms based on the filtering methods and the match relationships. Experimental results with real-life datasets confirm the effectiveness of our proposed algorithms.

Document-level relation extraction (RE) has recently received a lot of attention. However, existing models for document-level RE have similar structures to the models for sentence-level RE. Thus, they still do not consider some unique characteristics of the new problem setting. For example, in Wikipedia, there is a title for each page and it usually represents the topic entity that is mainly described on the page. In many cases, the topic entity is omitted in the text. Thus, existing RE models often fail to find the relations with the omitted topic entity. To tackle the problem, we propose a Topic-aware Relation EXtraction (T-REX) model. To extract the relations with the (possibly omitted) topic entity, the proposed model first encodes the topic entity by aggregating the information of all its mentions in the document. Then it finds the relations between the topic entity and each mention of other entities. Finally, the output layer combines the mention-wise results and outputs all relations expressed in the document. Our performance study with a large-scale dataset confirms the effectiveness of the T-REX model.

With the continuous emergence of new applications and cyberattacks and their frequent updates, the need for automatic protocol reverse engineering is gaining recognition. Although several methods for automatic protocol reverse engineering have been proposed, each method still faces major limitations in extracting clear specifications and in its universal application. In order to overcome such limitations, we propose an automatic protocol reverse engineering method using a two-pathway model based on a contiguous sequential pattern (CSP) algorithm. By using this model, the method can infer both command-oriented protocols and non-command-oriented protocols clearly and in detail. The proposed method infers all the key elements of the protocol, which are syntax, semantics, and finite state machine (FSM), and extracts clear syntax by defining fine-grained field types and three types of format: field format, message format, and flow format. We evaluated the efficacy of the proposed method over two non-command-oriented protocols and three command-oriented protocols: the former are HTTP and DNS, and the latter are FTP, SMTP, and POP3. The experimental results show that this method can reverse engineer with high coverage and correctness rates, more than 98.5% and 99.1% respectively, and be general for both command-oriented and non-command-oriented protocols.

As the amount of Internet traffic increases due to newly emerging applications and their malicious behaviors, the amount of traffic that must be analyzed is rapidly increasing. Many protocols that occur under these situations are unknown and undocumented. For efficient network management and security, a deep understanding of these protocols is required. Although many protocols reverse engineering methods have been introduced in the literature, there is still no single standardized method to completely extract a protocol specification, and each of the existing methods has some limitations. In this paper, we propose a novel protocol reverse engineering method to extract an intuitive and clear protocol specification. The proposed method extracts field formats, message formats, and flow formats as protocol syntax by using a contiguous sequential pattern algorithm three times hierarchically and defining four types of the field formats. Moreover, the proposed methods can extracts protocol semantics and a protocol finite state machine. The proposed method sufficiently compresses input messages into a small number of message formats in order to easily identify the intuitive structure of an unknown protocol. We implemented our method in a prototype system and evaluated the method to infer message formats of HTTP (a text protocol) and DNS (a binary protocol). The experimental results show that the proposed method infers HTTP with 100% correctness and 99% coverage. For DNS, the proposed method achieves 100% correctness and coverage.