Search

IEEE International Conference on Digital Health (ICDH) 2023 in IEEE World Congress on Services 2023, Healthcare organizations exchange sensitive health records, including behavioral health data, across peer-to-peer networks, and it is challenging to find and fix compliance issues proactively. The Healthcare industry anticipates a growing need to audit substance use disorder patient data, commonly referred to as Part 2 data, having been shared without a release of information signed by the patient. To address this need, we developed and evaluated a novel methodology to detect Part 2 data exchanged between organizations that integrates Blockchain technologies with knowledge graphs. We detect substance use disorder data in patient encounters exchanged using clinical terminology based upon the value sets provided by the National Institutes of Health for the Substance Abuse and Mental Health Services Administration. Generally, we consider sharing Part 2 data without consent as Byzantine medical faults, as they represent data shared between known and trusted network participants, that is valid, but is not relevant, and sharing it causes a breach. In this paper, we present our methodology in detail along with the experiment results. We model a medical network of hospitals based upon the most recent healthcare legislation, TEFCA, and generate synthetic patient encounter data dynamically in HL7 format. We convert exchanged encounter data into a knowledge graph data model so that we can use SNOMED-CT for identifying Part 2 data. For cohorts of 1,000 patients, we detect Part 2 data in a subset of their encounter data shared between organizations and log that securely on an Ethereum-based blockchain.

Proceedings of the Second International Conference on Weblogs and Social Media, Identifying topics and concepts associated with a set of documents is a task common to many applications. It can help in the annotation and categorization of documents and be used to model a person's current interests for improving search results, business intelligence or selecting appropriate advertisements. One approach is to associate a document with a set of topics selected from a fixed ontology or vocabulary of terms. We have investigated using Wikipedia's articles and associated pages as a topic ontology for this purpose. The benefits are that the ontology terms are developed through a social process, maintained and kept current by the Wikipedia community, represent a consensus view, and have meaning that can be understood simply by reading the associated Wikipedia page. We use Wikipedia articles and the category and article link graphs to predict concepts common to a set of documents. We describe several algorithms to aggregate and refine results, including the use of spreading activation to select the most appropriate terms. While the Wikipedia category graph can be used to predict generalized concepts, the article links graph helps by predicting more specific concepts and concepts not in the category hierarchy. Our experiments demonstrate the feasibility of extending the category system with new concepts identified as a union of pages from the page link graph.

Proceedings of the International Geoscience and Remote Sensing Symposium (IGARSS), We show how to leverage quantum annealers (QAs) to better select candidates in greedy algorithms. Unlike conventional greedy algorithms that employ problem-specific heuristics for making locally optimal choices at each stage, we use QAs that sample from the ground state of a problem-dependent Hamiltonians at cryogenic temperatures and use retrieved samples to estimate the probability distribution of problem variables. More specifically, we look at each spin of the Ising model as a random variable and contract all problem variables whose corresponding uncertainties are negligible. Our empirical results on a D-Wave 2000Q quantum processor demonstrate that the proposed quantum-assisted greedy algorithm (QAGA) scheme can find notably better solutions compared to the state-of-the-art techniques in the realm of quantum annealing.

Proceedings of the Second Workshop on Domain Adaptation for NLP, pages 122–139 April 20, 2021, We present a locality preserving loss (LPL) that improves the alignment between vector space embeddings while separating uncorrelated representations. Given two pretrained embedding manifolds, LPL optimizes a model to project an embedding and maintain its local neighborhood while aligning one manifold to another. This reduces the overall size of the dataset required to align the two in tasks such as crosslingual word alignment. We show that the LPL-based alignment between input vector spaces acts as a regularizer, leading to better and consistent accuracy than the baseline, especially when the size of the training set is small. We demonstrate the effectiveness of LPL-optimized alignment on semantic text similarity (STS), natural language inference (SNLI), multi-genre language inference (MNLI) and cross-lingual word alignment (CLA) showing consistent improvements, finding up to 16% improvement over our baseline in lower resource settings.

We present a general post-quantum error-correcting technique for quantum annealing, called multi-qubit correction (MQC), that views the evolution in an open-system as a Gibbs sampler and reduces a set of (first) excited states to a new synthetic state with lower energy value. After sampling from the ground state of a given (Ising) Hamiltonian, MQC compares pairs of excited states to recognize virtual tunnels—i.e., a group of qubits that changing their states simultaneously can result in a new state with lower energy—and successively converges to the ground state. Experimental results using D-Wave 2000Q quantum annealers demonstrate that MQC finds samples with notably lower energy values and also improves the reproducibility of results, compared to recent hardware/software advances in the realm of quantum annealing such as reverse quantum annealing, increased inter-sample delay, and classical pre/post-processing methods.

Mobile Application Development, Usability and Security, Sougata Mukherjea (Ed.), Contemporary smartphones are capable of generating and transmitting large amounts of data about their users. Recent advances in collaborative context modeling combined with a lack of adequate permission model for handling dynamic context sharing on mobile platforms have led to the emergence of a new class of mobile applications that can access and share embedded sensor and context data. Most of the time such data is used for providing tailored services to the user but it can lead to serious breaches of privacy. We use Semantic Web technologies to create a rich notion of context. We also discuss challenges for context aware mobile platforms and present approaches to manage data flow on these devices using semantically rich fine-grained context-based policies that allow users to define their privacy and security need using tools we provide.

AAAI Technical Report WS-94-02., This paper describes the design of and experimentation with the Knowledge Query and Manipulation Language( KQML), a new language and protocol for exchanging information and knowledge. This work is part a larger effort, the ARPA Knowledge Sharing Effort which is aimed at developing techniques and methodology for building large-scale knowledge bases which are sharable and reusable. KQML is both a message format and a message-handling protocol to support run-time knowledge sharing among agents. KQML can be used as a language for an application program to interact with an intelligent system or for two or more intelligent systems to share knowledgein support of cooperative problem solving. KQML focuses on an extensible set of performatives, which defines the permissible operations that agents may attempt on each other’s knowledge and goal stores. The performatives comprise a substrate on which to develop higher-level models of inter-agent interaction such as contract nets and negotiation. In addition, KQML provides a basic architecture for knowledge sharing through a special class of agent called communication facilitators which coordinate the interactions of other agents The ideas which underlie the evolving design of KQML are currently being explored through experimental prototype systems which are being used to support several testbeds in such areas as concurrent engineering, intelligent design and intelligent planning and scheduling.

Proceedings of the 2018 IEEE International Conference on Big Data, Seattle, Big data analytics related to consumer behavior, market analysis, opinions, and recommendation often deal with end user's derived and inferred data, along with the observed data. To ensure consumer data protection, rules defined by the European Union’s General Data Protection Regulation (EU GDPR) must be adhered to by every organization using Personally Identifiable Information (PII) data for Big Data analysis. Similarly, Payment Card Industry Data Security Standard (PCI DSS) has policy guidelines specifically for organizations handling consumer’s payment card data. Both data regulation policies are currently available only in textual format and require significant manual effort to ensure their compliance. We have developed an integrated, semantically rich Knowledge Graph (or Ontology) to represent the rules mandated by both PCI DSS and EU GDPR. In the Ontology, we have also identified the obligations defined in these regulations and related them with corresponding Cloud Security Alliance (CSA) controls. We have validated this Knowledge Graph against the data policies of major vendors that deal with Big Data. This Knowledge Graph that is available in the public domain can be used by Big Data practitioners to automate data protection compliance in their organization.

Proceedings of the 4th Workshop on Semantic Deep Learning (SemDeep-4, ISWC), Understanding large, structured documents like scholarly articles, requests for proposals or business reports is a complex and difficult task. It involves discovering a document's overall purpose and subject(s), understanding the function and meaning of its sections and subsections, and extracting low level entities and facts about them. In this research, we present a deep learning based document ontology to capture the general purpose semantic structure and domain specific semantic concepts from a large number of academic articles and business documents. The ontology is able to describe different functional parts of a document, which can be used to enhance semantic indexing for a better understanding by human beings and machines. We evaluate our models through extensive experiments on datasets of scholarly articles from arXiv and Request for Proposal documents.

IEEE International Conference on Collaboration and Internet Computing 2018, In an open source cloud computing platform such as OpenStack, operators use Role-Based Access Control (RBAC) model to grant access to cloud resources. However, these user-level role-based access control techniques fail to include comprehensive user context. We believe a situational aware framework will improve security by bringing in user's context to such cloud systems. In this paper, we create a semantically rich context-sensitive access control system for OpenStack by incorporating the user's current context attributes like location, time, etc. In a proof-of-concept implementation, we integrate a knowledge graph with our own access control system to express and enforce the contextual-situation policies in OpenStack. The proposed system provides enhanced, flexible access control while minimizing the overhead of altering the existing access control framework. We also discuss various use cases, to highlight the benefits of our system and show enforcement results.

Advanced metering infrastructure (AMI), one of the prime components of the smart grid, has many benefits like demand response and load management. Electricity theft, a key concern in AMI security since smart meters used in AMI are vulnerable to cyber attacks, causes millions of dollar in financial losses to utilities every year. In light of this problem, the authors propose an entropy-based electricity theft detection scheme to detect electricity theft by tracking the dynamics of consumption variations of the consumers. Relative entropy is used to compute the distance between probability distributions obtained from consumption variations. When electricity theft attacks are launched against AMI, the probability distribution of consumption variations deviates from historical consumption, thus leading to a larger relative entropy. The proposed method is tested on different attack scenarios using real smart-meter data. The results show that the proposed method detects electricity theft attacks with high detection probability.

There is a need for blood glucose monitoring techniques that eliminate the painful and invasive nature of current methods, while maintaining the reliability and accuracy of established medical technology. This research aims to ultimately address these shortcomings in critically ill pediatric patients. Presented in this work is an alternative, minimally invasive technique that uses microneedles (MN) for the collection of transdermal glucose (TG). Due to their comparable skin properties, diffusion studies were performed on full thickness Yucatan miniature pig skin mounted to an in-line diffusion flow cell and on different skin sites of human subjects. Collected TG samples were measured with a L255C mutant of the E. coli glucose-binding protein (GBP) with an attached fluorescent probe. The binding constant (Kd = 0.67 μM) revealed the micromolar sensitivity and high selectivity of the his-tagged GBP biosensor for glucose, making it suitable for TG measurements. In both the animal and human models, skin permeability and TG diffusion across the skin increased with MN application. For intact and MN-treated human skin, a significant positive linear correlation (r > 0.95, p < 0.01) existed between TG and BG. The micromolar sensitivity of GBP minimized the volume required for interstitial fluid glucose analysis allowing MN application time (30 s) to be shortened compared to other studies. This time reduction can help in eliminating skin irritation issues and improving practical use of the technique by caregivers in the hospital. In addition, the his-tagged optical biosensor used in this work can be immobilized and used with a portable sensing fluorometer device at the point of care (POC) making this minimally invasive technology more ideal for use in the pediatric intensive care unit.

In scientific disciplines where research findings have a strong impact on society, reducing the amount of time it takes to understand, synthesize and exploit the research is invaluable. Topic modeling is an effective technique for summarizing a collection of documents to find the main themes among them and to classify other documents that have a similar mixture of co-occurring words. We show how grounding a topic model with an ontology, extracted from a glossary of important domain phrases, improves the topics generated and makes them easier to understand. We apply and evaluate this method to the climate science domain. The result improves the topics generated and supports faster research understanding, discovery of social networks among researchers, and automatic ontology generation., To appear in Proc. of Semantic Web for Social Good Workshop of the Int. Semantic Web Conf., Oct 2018 and published as part of the book "Emerging Topics in Semantic Technologies. ISWC 2018 Satellite Events", E. Demidova, A.J. Zaveri, E. Simperl (Eds.), ISBN: 978-3-89838-736-1, 2018, AKA Verlag Berlin, (edited authors)

11th IEEE International Conference on Cloud Computing (CLOUD), The rollout of European Union’s General Data Protection Regulation (EU GDPR) will have a far-reaching effect on Cloud data privacy and compliance for both the Cloud Service Providers (Data Providers) and the Consumers (Data Consumers). GDPR mandates that organizations collecting and processing information related to EU citizens adhere to its articles irrespective of where they are located or where the data is stored. This regulation is currently available only in the textual format and so requires significant manual effort to ensure its compliance. We have developed a semantically rich Ontology (or knowledge graph) to represent the rules and regulations mandated for both the cloud data consumers and providers by EU GDPR. In the Ontology, we have identified the different roles and their corresponding obligations under the GDPR articles. This knowledge graph, that is available in public domain, is machine processable and will help in automating EU GDPR regulation compliance.

Proceedings of International Workshop on Semantic Evaluation (SemEval-2018), We describe the systems developed by the UMBC team for 2018 SemEval Task 8, SecureNLP (Semantic Extraction from CybersecUrity REports using Natural Language Processing). We participated in three of the sub-tasks: (1) classifying sentences as being relevant or irrelevant to malware, (2) predicting token labels for sentences, and (4) predicting attribute labels from the Malware Attribute Enumeration and Characterization vocabulary for defining malware characteristics. We achieved F1 scores of 50.34/18.0 (dev/test), 22.23 (test-data), and 31.98 (test-data) for Task1, Task2 and Task2 respectively. We also make our cybersecurity embeddings publicly available at https://bit.ly/cybr2vec.

6th International IBM Cloud Academy Conference ICACON 2018, Japan, Organizations often use Cloud based services to manage their financial transactions, like fees payment, invoice payment etc., with their end users. These services allow payment using credit cards and thus need to adhere to the Payment Card Industry Data Security Standard (PCI DSS) standard. To effectively manage this policy, educational institutions dealing with card transaction currently monitor their payment gateway flow manually in order to be compliant. We propose a novel approach to automate this process using semantic web technology and natural language processing. In this paper we describe our technical approach and the ontology that we have developed to automatically extract key terms and rules from various compliance documents and represent them in a machine processable knowledge graph. We used Semantic Web’s Web Ontology Language (OWL) to create this knowledge graph which is machine processable and so can contribute significantly in automating the continuous monitoring of credit card PII data operation, transfer and sharing.

2017 IEEE Power & Energy Society General Meeting, Cyber-attacks poses a serious threat to power system operation. False data injection attack (FDIA) is one such severe threat, if wisely constructed, can cause flawed estimation of power system states, thereby, leading to uneconomical and unsecured operation of power system. In recent years many methods are proposed to secure the smart grid against malicious cyber-events by protecting certain critical measurement sensors. However, making a system completely hack-proof is rather idealistic. In this paper, in addition to the research carried out in this space, we present a new Log transformation based method to detect the FDIA in real time with high probability. The detection probability of the proposed scheme is compared with existing method using IEEE 14 bus system.

Semantic textual similarity is a measure of the degree of semantic equivalence between two pieces of text. We describe the SemSim system and its performance in the *SEM 2013 and SemEval-2014 tasks on semantic textual similarity. At the core of our system lies a robust distributional word similarity component that combines latent semantic analysis and machine learning augmented with data from several linguistic resources. We used a simple term alignment algorithm to handle longer pieces of text. Additional wrappers and resources were used to handle task specific challenges that include processing Spanish text, comparing text sequences of different lengths, handling informal words and phrases, and matching words with sense definitions. In the *SEM 2013 task on Semantic Textual Similarity, our best performing system ranked first among the 89 submitted runs. In the SemEval-2014 task on Multilingual Semantic Textual Similarity, we ranked a close second in both the English and Spanish subtasks. In the SemEval-2014 task on Cross-Level Semantic Similarity, we ranked first in Sentence---Phrase, Phrase---Word, and Word---Sense subtasks and second in the Paragraph---Sentence subtask.

We describe an approach for identifying fine-grained entity types in heterogeneous data graphs that is effective for unstructured data or when the underlying ontologies or semantic schemas are unknown. Identifying fine-grained entity types, rather than a few high-level types, supports coreference resolution in heterogeneous graphs by reducing the number of possible coreference relations that must be considered. Big data problems that involve integrating data from multiple sources can benefit from our approach when the datas ontologies are unknown, inaccessible or semantically trivial. For such cases, we use supervised machine learning to map entity attributes and relations to a known set of attributes and relations from appropriate background knowledge bases to predict instance entity types. We evaluated this approach in experiments on data from DBpedia, Freebase, and Arnetminer using DBpedia as the background knowledge base.

The formation flying of an occulter with a telescope at the Sun-Earth L2 (SEL2) Libration Point can be a challenging problem. A good knowledge of the Restricted Three Body Problem dynamics is required to understand how these two spacecraft interact with each other in the SEL2 unstable environment, and how other perturbations such as Solar Radiation Pressure (SRP) affect their mutual trajectories. This paper focuses on the transfer trajectories to achieve specific relative positions between two spacecraft as they fly in formation at SEL2, and analyzes the relevance of SRP in this formation, using the Wide-Field Infrared Survey Telescope (WFIRST) and the Starshade occulter as an example. Given that WFIRST and Starshade have very different area-to-mass ratios, SRP will affect their motion in different ways, and their relative position can be key to reduce the ΔV cost. In this paper we intend on providing an explanation on how the relative position between both spacecrafts affects the transfer ΔV from one observation to the other using dynamical system theory and Floquet modes.

Proceedings of the First Workshop on Fact Extraction and Verification, We describe our system used in the 2018 FEVER shared task. The system employed a frame-based information retrieval approach to select Wikipedia sentences providing evidence and used a two-layer multilayer perceptron to classify a claim as correct or not. Our submission achieved a score of 0.3966 on the Evidence F1 metric with accuracy of 44.79%, and FEVER score of 0.2628 F1 points.

IEEE Intelligence and Security Informatics (IEEE ISI) 2018, The multilingual nature of the Internet increases complications in the cybersecurity community's ongoing efforts to strategically mine threat intelligence from OSINT data on the web. OSINT sources such as social media, blogs, and dark web vulnerability markets exist in diverse languages and hinder security analysts, who are unable to draw conclusions from intelligence in languages they don't understand. Although third party translation engines are growing stronger, they are unsuited for private security environments. First, sensitive intelligence is not a permitted input to third party engines due to privacy and confidentiality policies. In addition, third party engines produce generalized translations that tend to lack exclusive cybersecurity terminology. In this paper, we address these issues and describe our system that enables threat intelligence understanding across unfamiliar languages. We create a neural network based system that takes in cybersecurity data in a different language and outputs the respective English translation. The English translation can then be understood by an analyst, and can also serve as input to an AI based cyber-defense system that can take mitigative action. As a proof of concept, we have created a pipeline which takes Russian threats and generates its corresponding English, RDF, and vectorized representations. Our network optimizes translations on specifically, cybersecurity data.

3rd IEEE International Conference on Collaboration and Internet Computing, Context-sensitive access control has been a research topic within mobile computing for more than a decade. Much of the work has focused on modeling context and representing policies. Choosing an appropriate policy for a user, however, remains a challenging goal. Creating usable mobile access control solutions have been researched from a users permission control perspective. We present a study carried out with subjects using their personal mobile devices that captures individualized policies through an iterative user feedback process. Policy precision, also referred to as "Violation Metric" (VM), was used to decide when all necessary policies had been captured. The feedback process used a hierarchical context ontology to represent user-context and gathered contextual-situations in which a policy would be applicable. The study also investigated the feasibility of using the VM measure to determine completion of the capture process for the users personalized access control policies, that handles their mobile privacy and security needs. Using an appropriate predefined policy is shown to have lesser user impact when trying to personalize access control policies for users.

2017 IEEE International Conference on Big Data (BIGDATA), With increasing regulation of Big Data, it is becoming essential for organizations to ensure compliance with various data protection standards. The Federal Acquisition Regulations System (FARS) within the Code of Federal Regulations (CFR) includes facts and rules for individuals and organizations seeking to do business with the US Federal government. Parsing and gathering knowledge from such lengthy regulation documents is currently done manually and is time and human intensive. Hence, developing a cognitive assistant for automated analysis of such legal documents has become a necessity. We have developed semantically rich approach to automate the analysis of legal documents and have implemented a system to capture various facts and rules contributing towards building an efficient legal knowledge base that contains details of the relationships between various legal elements, semantically similar terminologies, deontic expressions and cross-referenced legal facts and rules. In this paper, we describe our framework along with the results of automating knowledge extraction from the FARS document (Title 48, CFR). Our approach can be used by Big Data Users to automate knowledge extraction from Large Legal documents

4th IEEE/ACM International Conference on Big Data Computing, Applications and Technologies, Current language understanding approaches focus on small documents, such as newswire articles, blog posts, product reviews and discussion forum discussions. Understanding and extracting information from large documents like legal briefs, proposals, technical manuals and research articles is still a challenging task. We describe a framework that can analyze a large document and help people to locate desired information in it. We aim to automatically identify and classify different sections of documents and understand their purpose within the document. A key contribution of our research is modeling and extracting the logical structure of electronic documents using machine learning techniques, including deep learning. We also make available a dataset of information about a collection of scholarly articles from the arXiv eprints collection that includes a wide range of metadata for each article, including a table of contents, section labels, section summarizations and more. We hope that this dataset will be a useful resource for the machine learning and language understanding communities for information retrieval, content-based question answering and language modeling tasks.

IEEE International Conference on Big Data, We describe an approach using dynamic topic modeling to model influence and predict future trends in a scientific discipline. Our study focuses on climate change and uses assessment reports of the Intergovernmental Panel on Climate Change (IPCC) and the papers they cite. Since 1990, an IPCC report has been published every five years that includes four separate volumes, each of which has many chapters. Each report cites tens of thousands of research papers, which comprise a correlated dataset of temporally grounded documents. We use a custom dynamic topic modeling algorithm to generate topics for both datasets and apply crossdomain analytics to identify the correlations between the IPCC chapters and their cited documents. The approach reveals both the influence of the cited research on the reports and how previous research citations have evolved over time. For the IPCC use case, the report topic model used 410 documents and a vocabulary of 5911 terms while the citations topic model was based on 200K research papers and a vocabulary more than 25K terms. We show that our approach can predict the importance of its extracted topics on future IPCC assessments through the use of cross domain correlations, Jensen-Shannon divergences and cluster analytics.

IEEE 2nd International Conference on Signal and Image Processing (ICSIP’17), In this paper, the secrecy outage probability of threshold-based decode-and-forward (DF) cooperative relay network is evaluated. Unlike other works to date, we assume combining of direct and relayed signals both at the destination and the eavesdropper. All the links undergo Rayleigh fading and the relay can perfectly decode the message, only if the received SNR meets a particular threshold. The secrecy performance is compared for the system with either selection combining (SC), or with maximal ratio combining (MRC) or with the combination of both, at the destination and eavesdropper. We have shown that the eavesdropper channel quality, required secrecy rate, pre-defined threshold and the choice of diversity scheme significantly affects the secrecy performance of the system.

8th International Joint Conference on Natural Language Processing (System Demonstrations), Computer Assisted Discovery Extraction and Translation (CADET) is a workbench for helping knowledge workers find, label, and translate documents of interest. It combines a multitude of analytics together with a flexible environment for customizing the workflow for different users. This open-source framework allows for easy development of new research prototypes using a micro-service architecture based atop Docker and Apache Thrift.

2017 Twenty-third National Conference on Communications (NCC), In this paper, a source communicates to the destination with the cooperation of a relay, in the presence of an eavesdropper. All the links undergo Rayleigh fading and perfect decoding at the relays is not considered. The secrecy outage probability expression is evaluated for a decode-and-forward (DF) dual-hop cooperative relay network, both with and without the presence of direct source to eavesdropper transmission link. The performance of the maximal ratio combining (MRC) and selection combining (SC) diversity at the eavesdropper is investigated. Asymptotic and diversity gain analysis for both the single relay and multi-relay system is obtained, when average SNRs of source-relay and relay-destination links are balanced or unbalanced. We have shown that the increase in target secrecy rate and eavesdropper channel quality significantly affects the outage performance of the system. We have investigated the outage probability of optimal relay selection scheme, when either full instantaneous channel state information (ICSI) or statistical channel state information (SCSI) of all the links is available and have shown that there is improvement in the secrecy performance with the increase in the number of relays

Proceedings of the Doctoral Consortium at the 16th International Semantic Web Conference, My dissertation research is developing an approach to identify and explain errors in a knowledge graph constructed by extracting entities and relations from text. Information extraction systems can automatically construct knowledge graphs from a large collection of documents, which might be drawn from news articles, Web pages, social media posts or discussion forums. The language understanding task is challenging and current extraction systems introduce many kinds of errors. Previous work on improving the quality of knowledge graphs uses additional evidence from background knowledge bases or Web searches. Such approaches are di cult to apply when emerging entities are present and/or only one knowledge graph is available. In order to address the problem I am using multiple complementary techniques including entity linking, common sense reasoning, and linguistic analysis.

False data injection attacks can pose serious threats to the operation and control of power grid. The smarter the power grid gets, the more vulnerable it becomes to cyber attacks. Various detection methods of cyber attacks have been proposed in the literature in recent past. However, to completely alleviate the possibility of cyber threats, the compromised meters must be identified and secured. In this paper, we are presenting an Artificial Intelligence (AI) based identification method to correctly single out the malicious meters. The proposed AI based method successfully identifies the compromised meters by anticipating the correct measurements in the event of the cyber attack. NYISO load data is mapped with the IEEE 14 bus system to validate the proposed method. The efficiency of the proposed method is compared for Artificial Neural Network (ANN) and Extreme Learning Machine (ELM) based AI techniques. It is observed that both the techniques identify the corrupted meters with high accuracy.

Proceedings of the First IEEE International Conference on Edge Computing, Securing their critical documents on the cloud from data threats is a major challenge faced by organizations today. Controlling and limiting access to such documents requires a robust and trustworthy access control mechanism. In this paper, we propose a semantically rich access control system that employs an access broker module to evaluate access decisions based on rules generated using the organizations confidentiality policies. The proposed system analyzes the multi-valued attributes of the user making the request and the requested document that is stored on a cloud service platform, before making an access decision. Furthermore, our system guarantees an end-to-end oblivious data transaction between the organization and the cloud service provider using oblivious storage techniques. Thus, an organization can use our system to secure their documents as well as obscure their access pattern details from an untrusted cloud service provider.

Knowledge graphs and vector space models are robust knowledge representation techniques with individual strengths and weaknesses. Vector space models excel at determining similarity between concepts, but are severely constrained when evaluating complex dependency relations and other logic-based operations that are a strength of knowledge graphs. We describe the VKG structure that helps unify knowledge graphs and vector representation of entities, and enables powerful inference methods and search capabilities that combine their complementary strengths. We analogize this to thinking `fast' in vector space along with thinking 'slow' and `deeply' by reasoning over the knowledge graph. We have created a query processing engine that takes complex queries and decomposes them into subqueries optimized to run on the respective knowledge graph or vector view of a VKG. We show that the VKG structure can process specific queries that are not efficiently handled by vector spaces or knowledge graphs alone. We also demonstrate and evaluate the VKG structure and the query processing engine by developing a system called Cyber-All-Intel for knowledge extraction, representation and querying in an end-to-end pipeline grounded in the cybersecurity informatics domain.

IEEE Transactions on Industrial Informatics, For reliable operation and control of smart grid, estimating the correct states is of utmost importance to the system operator. With recent incorporation of information technology and advanced metering infrastructure, the futuristic grid is more prone to cyber-threats. The false data injection (FDI) attack is one of the most thoroughly researched cyber-attacks. Intelligently crafted, it can cause false estimation of states, which further seriously affects the entire power system operation. In this paper, we propose joint-transformation-based scheme to detect FDI attacks in real time. The proposed method is built on the dynamics of measurement variations. Kullback-Leibler distance is used to find out the difference between probability distributions obtained from measurement variations. The proposed method is tested using IEEE 14 bus system considering attack on different state variables. The results shows that the proposed scheme detects FDI attacks with high detection probability

Industrial Knowledge Graphs, Digital Twin models are computerized clones of physical assets that can be used for in-depth analysis. Industrial production lines tend to have multiple sensors to generate near real-time status information for production. Industrial Internet of Things datasets are difficult to analyze and infer valuable insights such as points of failure, estimated overhead. etc. In this paper we introduce a simple way of formalizing knowledge as digital twin models coming from sensors in industrial production lines. We present a way on to extract and infer knowledge from large scale production line data, and enhance manufacturing process management with reasoning capabilities, by introducing a semantic query mechanism. Our system primarily utilizes a graph-based query language equivalent to conjunctive queries and has been enriched with inference rules.

Conventional power system was originally designed to provide efficient and reliable power. With the integration of information technology and advanced metering infrastructure, the power grid has become smart. The smart meters have allowed the system operators to continuously monitor the power system in real time and take necessary action to avoid system failures. Malicious actor, with access to the smart meters can modify sensor measurements to disrupt the operation of power system. To make the power system resilient to such cyber-attacks, it is important to study all possible outcomes of cyber-intrusions. In this paper, we present an attack on security constrained optimum power flow. We show with the help of case studies how an attacker, by injecting false data in load measurement sensors, can force system operator to change the dispatch and hence make the power system N–1 in-compliant. The attack is modeled as a bi-level optimization problem, aiming to find the minimum set of sensors required to launch the attack. From the system operator's perspective, critical lines and critical generators vulnerable to false data injection (FDI) attack are identified. IEEE 14 bus and 30 bus test systems are used to test the vulnerability of the power system against FDI attacks.

12th Annual Symposium On Information Assurance (ASIA’17), —In this paper, we consider a source, which communicates to destination, with cooperation of a relay node. An eavesdropper is tapping the second hop, when all the links undergo Rayleigh fading. Relay nodes are the market players, who compete to trade their power to source in order to maximize their incentives. We evaluate the secrecy outage probability of a dual-hop decode-and-forward (DF) threshold- based cooperative relay network. Without assuming that all the relays can always perfectly decode, here we consider that only those relays who satisfy predetermined threshold, can correctly decode the message. We evaluate the utility of relays for both linear/non-linear and static/dynamic Cournot duopoly asymmetric model. We have shown that increase in channel gain from relay to eavesdropper, decreases the profit of relays and can have a dramatic effect on the Nash outcome.

Fifth International IBM Cloud Academy Conference, Educational organizations, like Universities and School Systems, are rapidly adopting Cloud based services to provide Information Technology (IT) infrastructure to their students. These include course offerings, class materials, ​data storage, emailing and collaboration software, virtual computing environment, etc. Moreover, cloud providers, like Amazon, are also providing free computing credits targeted to students. The legal documents associated with cloud based services, such as Service Level Agreements (SLAs), provide information regarding quality and use of cloud services. These documents are often long text-based documents containing domain specific terminology. In addition, this terminology varies from one document or service provider to another. We propose a framework to extract semantically similar terms and entities across cloud service documents using word embeddings and neural networks. Our work is intended to aid cloud service consumers across a variety of fields by providing the ability to understand the services and requirements offered by large-scale commercial cloud services. In some of our previous papers, we have used semantic web and natural language processing to analyze SLA and privacy policy documents for cloud services [1, 2, 3]. In this work, we extend our approach to propose a deep learning-based technique to analyze these documents and populate cloud service ontologies. The preliminary analysis of cloud SLAs documents performed by us showed that deep learning techniques are useful in context disambiguation and identifying semantically similar terminology across services.

System calls provide an interface to the services made available by an operating system. As a result, any functionality provided by a software application eventually reduces to a set of fixed system calls. Since system calls have been used in literature, to analyze program behavior we made an assumption that analyzing the patterns in calls made by a mobile application would provide us insight into its behavior. In this paper, we present our preliminary study conducted with 534 mobile applications and the system calls made by them. Due to a rising trend of mobile applications providing multiple functionalities, our study concluded, mapping system calls to functional behavior of a mobile application was not straightforward. We use Weka tool with manually annotated application behavior classes and system call features in our experiments, to show that using such features achieves mediocre F1-measure at best. Thus leading to the conclusion that system calls were not sufficient features for mobile application behavior classification.

SDM 2016 Doctoral Forum, SIAM International Conference on Data Mining, Up-to-the-minute language understanding approaches are mostly focused on small documents such as newswire articles, blog posts, product reviews and discussion forum en- tries. Understanding and extracting information from large documents such as legal documents, reports, proposals, technical manuals and research articles is still a challenging task. The reason behind this challenge is that the documents may be multi-themed, complex and cover diverse topics. For example, business opportunities may contain information on the background of the business, product or service of the business, plan, team management, financial or budget related data, competitors, logistics, compliance, legal information and boilerplate content that is repeated across documents. The content can be split into multiple files or aggregated into one large file. As a result, the content in the whole document may have different structures and formats. Furthermore, the information is expressed in different forms such as paragraphs of text, headers, data forms, tables, images, mathematical equations, lists or a nested combination of these structures.

In 2016, the International City/County Management Association (ICMA), in partnership with the University of Maryland, Baltimore County (UMBC), conducted a survey to better understand local government cybersecurity practices. The results of this survey provide insights into the cybersecurity issues faced by U.S. local governments, including what their capacities are, what kind of barriers they face, and what type of support they have to implement cybersecurity programs.

This study evaluates the intercept and outage probability of a decode-and-forward (DF) underlay cognitive radio network. The secondary users are subject to interference limitations from the primary network, with an eavesdropper tapping the second hop of cognitive network, when all the links undergo Rayleigh fading. For this threshold-based system, without assuming that the DF relays can always decode the message correctly, here the authors consider that only a set of relays whose SNR satisfies a predetermined threshold can decode the message successfully. The authors have obtained asymptotic analysis for both cases, when average SNRs of secondary source-relay and relay-destination links are balanced or unbalanced. The authors have shown that the desired secrecy rate, predetermined threshold, eavesdropper channel quality and interference power limitations significantly affects the secrecy performance of the cognitive radio system. They have investigated the outage and intercept probability of relay selection scheme, when either full instantaneous channel state information or statistical channel state information of all the links is available. They have shown that the optimal relay selection improves the performance of the multi-relay cognitive system, when the number of relays is increased.

37th IEEE Sarnoff Symposium (2016), The number of sensors, actuators and electronic control units present in cars have increased in the last few years. The Internet-of-Things (IoT) model has transformed modern vehicles into a co-engineered interacting network of physical and computational components. Vehicles have become a complex cyber-physical system where context detection has become a challenge. In this paper, we present a rule based approach for context detection in vehicles. We also discuss various attack surfaces and vulnerabilities in vehicular IoT. We propose a system which collects data from the CAN bus and uses it to generate SWRL rules. We then reason over these rules to mine vehicular context. We also showcase a few use-cases as examples where our system can detect if a vehicle is in an unsafe/anomalous state

International Conference on Cloud Computing, Consumers want to ensure that their enterprise data is stored securely and obliviously on the cloud, such that the data objects or their access patterns are not revealed to anyone, including the cloud provider, in the public cloud environment. We have created a detailed ontology describing the oblivious cloud stor-age models and role based access controls that should be in place to manage this risk. We have developed an algorithm to store cloud data using oblivious data structure defined in this paper. We have also implemented the ObliviCloudManager ap-plication that allows users to manage their cloud data by vali-dating it before storing it in an oblivious data structure. Our application uses role-based access control model and collection based document management to store and retrieve data effi-ciently. Cloud consumers can use our system to define policies for storing data obliviously and manage storage on untrusted cloud platforms even if they are unfamiliar with the underlying technology and concepts of oblivious data structures.

IEEE International Conference on Cloud Computing, With the increase in the number of cloud services and service providers, manual analysis of Service Level Agreements (SLA), comparison between different service offerings and conformance regulation has become a difficult task for customers. Cloud SLAs are policy documents describing the legal agreement between cloud providers and customers. SLA specifies the commitment of availability, performance of services, penalties associated with violations and procedure for customers to receive compensations in case of service disruptions. The aim of our research is to develop technology solutions for automated cloud service management using Semantic Web and Text Mining techniques. In this paper we discuss in detail the challenges in automating cloud services management and present our preliminary work in extraction of knowledge from SLAs of different cloud services. We extracted two types of information from the SLA documents which can be useful for end users. First, the relationship between the service commitment and financial credit. We represented this information by enhancing the existing Cloud service ontology proposed by us in our previous research. Second, we extracted rules in the form of obligations and permissions from SLAs using modal and deontic logic formalizations. For our analysis, we considered six publicly available SLA documents from different cloud computing service providers.

Climate change is an important social issue and the subject of much research, both to understand the history of the Earth’s changing climate and to foresee what changes to expect in the future. Approximately every five years starting in 1990 the Intergovernmental Panel on Climate Change (IPCC) publishes a set of reports that cover the current state of climate change research, how this research will impact the world, risks, and approaches to mitigate the effects of climate change. Each report supports its findings with hundreds of thousands of citations to scientific journals and reviews by governmental policy makers. Analyzing trends in the cited documents over the past 30 years provides insights into both an evolving scientific field and the climate change phenomenon itself. Presented in this paper are results of dynamic topic modeling to model the evolution of these climate change reports and their supporting research citations over a 30 year time period. Using this technique shows how the research influences the assessment reports and how trends based on these influences can affect future assessment reports. This is done by calculating cross-domain divergences between the citation domain and the assessment report domain and by clustering documents between domains. This approach could be applied to other social problems with similar structure such as disaster recovery.

With the advent of numerous online content providers, utilities and applications, each with their own specific version of privacy policies and its associated overhead, it is becoming increasingly difficult for concerned users to manage and track the confidential information that they share with the providers. Users consent to providers to gather and share their Personally Identifiable Information (PII). We have developed a novel framework to automatically track details about how a users' PII data is stored, used and shared by the provider. We have integrated our Data Privacy ontology with the properties of blockchain, to develop an automated access control and audit mechanism that enforces users' data privacy policies when sharing their data across third parties. We have also validated this framework by implementing a working system LinkShare. In this paper, we describe our framework on detail along with the LinkShare system. Our approach can be adopted by Big Data users to automatically apply their privacy policy on data operations and track the flow of that data across various stakeholders., Comment: 10 pages, 6 figures, Published in: 4th International Workshop on Privacy and Security of Big Data (PSBD 2017) in conjunction with 2017 IEEE International Conference on Big Data (IEEE BigData 2017) December 14, 2017, Boston, MA, USA

17th IEEE International Conference on Information Reuse and Integration, Data from computer log files record traces of events involving user activity, applications, system software and network traffic. Logs are usually intended for diagnostic and debugging purposes, but their data can be extremely useful in system audits and forensic investigations. Logs created by intrusion detection systems, web servers, anti-virus and anti-malware systems, firewalls and network devices have information that can reconstruct the activities of malware or a malicious agent, help plan for remediation and prevent attacks by revealing probes or intrusions before damage has been done. While existing tools like Splunk can help analyze logs with known schemas, understanding log whose format is unfamiliar or associated with new device or custom application can be challenging. We describe a framework for analyzing logs and automatically generating a semantic description of their schema and content in RDF. The framework begins by normalizing the log into columns and rows using regular expression-based and dictionary-based classifiers. Leveraging our existing work on inferring the semantics of tables, we associate semantic types with columns and, when possible, map them to concepts in general knowledge-bases (e.g. DBpedia) and domain specific ones (e.g., Unified Cybersecurity Ontology). We link cell values to known type instances (e.g., an IP address) and suggest relationships between columns. Converting large and verbose log files into such semantic representations reveals their meaning and supports search, integration and reasoning over the data.

2016 IEEE International Symposium on Nanoelectronic and Information Systems (iNIS), In the quest for reliability and automation, the entire smart grid operation and control depends on the communication infrastructure. This reliance on the information and communication technologies has also opened up possibilities of cyber intrusions. In this paper, a bid modification attack on the power exchange server is presented with the aim of gaining monetary benefits in the real-time power market. The attack is modelled for PJM 5 bus and IEEE 14 bus test system. The minimum number of load bids required to be changed for launching the attack is obtained and impacts on real time locational marginal prices (LMPs) are presented.

Big Data Challenges, Research, and Technologies in the Earth and Planetary Sciences Workshop, IEEE Int. Conf. on Big Data, A common Big Data problem is the need to integrate large temporal data sets from various data sources into one comprehensive structure. Having the ability to correlate evolving facts between data sources can be especially useful in supporting a number of desired application functions such as inference and influence identification. As a real world application we use climate change publications based on the Intergovernmental Panel on Climate Change, which publishes climate change assessment reports every five years, with currently over 25 years of published content. Often these reports reference thousands of research papers. We use dynamic topic modeling as a basis for combining report and citation domains into one structure. We are able to correlate documents between the two domains to understand how the research has influenced the reports and how this influence has changed over time. In this use case, the topic report model used a total number of 410 documents and 5911 terms in the vocabulary while in the topic citations the vocabulary consisted of 25,154 terms and the number of documents was closer to 200,000 research papers.