Visible to the public Biblio

Found 745 results

Filters: Keyword is security of data  [Clear All Filters]
Wei, Shengjun, Zhong, Hao, Shan, Chun, Ye, Lin, Du, Xiaojiang, Guizani, Mohsen.  2018.  Vulnerability Prediction Based on Weighted Software Network for Secure Software Building. 2018 IEEE Global Communications Conference (GLOBECOM). :1-6.

To build a secure communications software, Vulnerability Prediction Models (VPMs) are used to predict vulnerable software modules in the software system before software security testing. At present many software security metrics have been proposed to design a VPM. In this paper, we predict vulnerable classes in a software system by establishing the system's weighted software network. The metrics are obtained from the nodes' attributes in the weighted software network. We design and implement a crawler tool to collect all public security vulnerabilities in Mozilla Firefox. Based on these data, the prediction model is trained and tested. The results show that the VPM based on weighted software network has a good performance in accuracy, precision, and recall. Compared to other studies, it shows that the performance of prediction has been improved greatly in Pr and Re.

Subahi, Alanoud, Theodorakopoulos, George.  2018.  Ensuring Compliance of IoT Devices with Their Privacy Policy Agreement. 2018 IEEE 6th International Conference on Future Internet of Things and Cloud (FiCloud). :100–107.
In the past few years, Internet of Things (IoT) devices have emerged and spread everywhere. Many researchers have been motivated to study the security issues of IoT devices due to the sensitive information they carry about their owners. Privacy is not simply about encryption and access authorization, but also about what kind of information is transmitted, how it used and to whom it will be shared with. Thus, IoT manufacturers should be compelled to issue Privacy Policy Agreements for their respective devices as well as ensure that the actual behavior of the IoT device complies with the issued privacy policy. In this paper, we implement a test bed for ensuring compliance of Internet of Things data disclosure to the corresponding privacy policy. The fundamental approach used in the test bed is to capture the data traffic between the IoT device and the cloud, between the IoT device and its application on the smart-phone, and between the IoT application and the cloud and analyze those packets for various features. We test 11 IoT manufacturers and the results reveal that half of those IoT manufacturers do not have an adequate privacy policy specifically for their IoT devices. In addition, we prove that the action of two IoT devices does not comply with what they stated in their privacy policy agreement.
Al-Hasnawi, Abduljaleel, Mohammed, Ihab, Al-Gburi, Ahmed.  2018.  Performance Evaluation of the Policy Enforcement Fog Module for Protecting Privacy of IoT Data. 2018 IEEE International Conference on Electro/Information Technology (EIT). :0951–0957.
The rapid development of the Internet of Things (IoT) results in generating massive amounts of data. Significant portions of these data are sensitive since they reflect (directly or indirectly) peoples' behaviors, interests, lifestyles, etc. Protecting sensitive IoT data from privacy violations is a challenge since these data need to be communicated, processed, analyzed, and stored by public networks, servers, and clouds; most of them are untrusted parties for data owners. We propose a solution for protecting sensitive IoT data called Policy Enforcement Fog Module (PEFM). The major task of the PEFM solution is mandatory enforcement of privacy policies for sensitive IoT data-wherever these data are accessed throughout their entire lifecycle. The key feature of PEFM is its placement within the fog computing infrastructure, which assures that PEFM operates as closely as possible to data sources within the edge. PEFM enforces policies directly for local IoT applications. In contrast, for remote applications, PEFM provides a self-protecting mechanism based on creating and disseminating Active Data Bundles (ADBs). ADBs are software constructs bundling inseparably sensitive data, their privacy policies, and an execution engine able to enforce privacy policies. To prove effectiveness and efficiency of the proposed module, we developed a smart home proof-of-concept scenario. We investigate privacy threats for sensitive IoT data. We run simulation experiments, based on network calculus, for testing performance of the PEFM controls for different network configurations. The results of the simulation show that-even with using from 1 to 5 additional privacy policies for improved data privacy-penalties in terms of execution time and delay are reasonable (approx. 12-15% and 13-19%, respectively). The results also show that PEFM is scalable regarding the number of the real-time constraints for real-time IoT applications.
Martiny, Karsten, Elenius, Daniel, Denker, Grit.  2018.  Protecting Privacy with a Declarative Policy Framework. 2018 IEEE 12th International Conference on Semantic Computing (ICSC). :227–234.
This article describes a privacy policy framework that can represent and reason about complex privacy policies. By using a Common Data Model together with a formal shareability theory, this framework enables the specification of expressive policies in a concise way without burdening the user with technical details of the underlying formalism. We also build a privacy policy decision engine that implements the framework and that has been deployed as the policy decision point in a novel enterprise privacy prototype system. Our policy decision engine supports two main uses: (1) interfacing with user interfaces for the creation, validation, and management of privacy policies; and (2) interfacing with systems that manage data requests and replies by coordinating privacy policy engine decisions and access to (encrypted) databases using various privacy enhancing technologies.
Vegda, Hiral, Modi, Nimesh.  2018.  Secure and Efficient Approach to Prevent Ad Hoc Network Attacks Using Intrusion Detection System. 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS). :129-133.

In Ad hoc networks the main purpose is communication without infrastructure and there are many implementations already done on that. There is little effort done for security to prevent threats in ad hoc networks (like MANETs). It is already proven that; there is no any centralized mechanism for defence against threats, such as a firewall, an intrusion detection system, or a proxy in ad hoc networks. Ad hoc networks are very convenient due to its features like self-maintenance, self-organizing and providing wireless communication. In Ad hoc networks there is no fixed infrastructure in which every node works like simply a router which stores and forwards packet to final destination. Due to these dynamic topology features, Ad hoc networks are anywhere, anytime. Therefore, it is necessary to make a secure mechanism for the ad hoc components so that with flexibility they have that security also. This paper shows the secure and flexible implementation about to protect any ad hoc networks. This proposed system design is perfect solution to provide security with flexibility by providing a hybrid system which combines ECC and MAES to detect and prevent Ad hoc network attacks using Intrusion detection system. The complete proposed system designed on NS 2.35 software using Ubuntu (Linux) OS.

Li, Teng, Ma, Jianfeng, Pei, Qingqi, Shen, Yulong, Sun, Cong.  2018.  Anomalies Detection of Routers Based on Multiple Information Learning. 2018 International Conference on Networking and Network Applications (NaNA). :206-211.

Routers are important devices in the networks that carry the burden of transmitting information among the communication devices on the Internet. If a malicious adversary wants to intercept the information or paralyze the network, it can directly attack the routers and then achieve the suspicious goals. Thus, preventing router security is of great importance. However, router systems are notoriously difficult to understand or diagnose for their inaccessibility and heterogeneity. The common way of gaining access to the router system and detecting the anomaly behaviors is to inspect the router syslogs or monitor the packets of information flowing to the routers. These approaches just diagnose the routers from one aspect but do not consider them from multiple views. In this paper, we propose an approach to detect the anomalies and faults of the routers with multiple information learning. We try to use the routers' information not from the developer's view but from the user' s view, which does not need any expert knowledge. First, we do the offline learning to transform the benign or corrupted user actions into the syslogs. Then, we try to decide whether the input routers' conditions are poor or not with clustering. During the detection phase, we use the distance between the event and the cluster to decide if it is the anomaly event and we can provide the corresponding solutions. We have applied our approach in a university network which contains Cisco, Huawei and Dlink routers for three months. We aligned our experiment with former work as a baseline for comparison. Our approach can gain 89.6% accuracy in detecting the attacks which is 5.1% higher than the former work. The results show that our approach performs in limited time as well as memory usages and has high detection and low false positives.

Harrison, William L., Allwein, Gerard.  2018.  Semantics-Directed Prototyping of Hardware Runtime Monitors. 2018 International Symposium on Rapid System Prototyping (RSP). :42-48.

Building memory protection mechanisms into embedded hardware is attractive because it has the potential to neutralize a host of software-based attacks with relatively small performance overhead. A hardware monitor, being at the lowest level of the system stack, is more difficult to bypass than a software monitor and hardware-based protections are also potentially more fine-grained than is possible in software: an individual instruction executing on a processor may entail multiple memory accesses, all of which may be tracked in hardware. Finally, hardware-based protection can be performed without the necessity of altering application binaries. This article presents a proof-of-concept codesign of a small embedded processor with a hardware monitor protecting against ROP-style code reuse attacks. While the case study is small, it indicates, we argue, an approach to rapid-prototyping runtime monitors in hardware that is quick, flexible, and extensible as well as being amenable to formal verification.

Wang, Jingyuan, Xie, Peidai, Wang, Yongjun, Rong, Zelin.  2018.  A Survey of Return-Oriented Programming Attack, Defense and Its Benign Use. 2018 13th Asia Joint Conference on Information Security (AsiaJCIS). :83-88.

The return-oriented programming(ROP) attack has been a common access to exploit software vulnerabilities in the modern operating system(OS). An attacker can execute arbitrary code with the aid of ROP despite security mechanisms are involved in OS. In order to mitigate ROP attack, defense mechanisms are also drawn researchers' attention. Besides, research on the benign use of ROP become a hot spot in recent years, since ROP has a perfect resistance to static analysis, which can be adapted to hide some important code. The results in benign use also benefit from a low overhead on program size. The paper discusses the concepts of ROP attack as well as extended ROP attack in recent years. Corresponding defense mechanisms based on randomization, frequency, and control flow integrity are analyzed as well, besides, we also analyzed limitations in this defense mechanisms. Later, we discussed the benign use of ROP in steganography, code integrity verification, and software watermarking, which showed the significant promotion by adopting ROP. At the end of this paper, we looked into the development of ROP attack, the future of possible mitigation strategies and the potential for benign use.

Khan, Muhammad Imran, O’Sullivan, Barry, Foley, Simon N..  2018.  Towards Modelling Insiders Behaviour as Rare Behaviour to Detect Malicious RDBMS Access. 2018 IEEE International Conference on Big Data (Big Data). :3094–3099.
The heart of any enterprise is its databases where the application data is stored. Organizations frequently place certain access control mechanisms to prevent access by unauthorized employees. However, there is persistent concern about malicious insiders. Anomaly-based intrusion detection systems are known to have the potential to detect insider attacks. Accurate modelling of insiders behaviour within the framework of Relational Database Management Systems (RDBMS) requires attention. The majority of past research considers SQL queries in isolation when modelling insiders behaviour. However, a query in isolation can be safe, while a sequence of queries might result in malicious access. In this work, we consider sequences of SQL queries when modelling behaviours to detect malicious RDBMS accesses using frequent and rare item-sets mining. Preliminary results demonstrate that the proposed approach has the potential to detect malicious RDBMS accesses by insiders.
Tufail, Hina, Zafar, Kashif, Baig, Rauf.  2018.  Digital Watermarking for Relational Database Security Using mRMR Based Binary Bat Algorithm. 2018 17th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/ 12th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE). :1948–1954.
Publically available relational data without security protection may cause data protection issues. Watermarking facilitates solution for remote sharing of relational database by ensuring data integrity and security. In this research, a reversible watermarking for numerical relational database by using evolutionary technique has been proposed that ensure the integrity of underlying data and robustness of watermark. Moreover, mRMR based feature subset selection technique has been used to select attributes for implementation of watermark instead of watermarking whole database. Binary Bat algorithm has been used as constraints optimization technique for watermark creation. Experimental results have shown the effectiveness of the proposed technique against data tempering attacks. In case of alteration attacks, almost 70% data has been recovered, 50% in deletion attacks and 100% data is retrieved after insertion attacks. The watermarking based on evolutionary technique (WET) i.e., mRMR based Binary Bat Algorithm ensures the data accuracy and it is resilient against malicious attacks.
Ghose, Nirnimesh, Lazos, Loukas, Li, Ming.  2018.  Secure Device Bootstrapping Without Secrets Resistant to Signal Manipulation Attacks. 2018 IEEE Symposium on Security and Privacy (SP). :819-835.
In this paper, we address the fundamental problem of securely bootstrapping a group of wireless devices to a hub, when none of the devices share prior associations (secrets) with the hub or between them. This scenario aligns with the secure deployment of body area networks, IoT, medical devices, industrial automation sensors, autonomous vehicles, and others. We develop VERSE, a physical-layer group message integrity verification primitive that effectively detects advanced wireless signal manipulations that can be used to launch man-in-the-middle (MitM) attacks over wireless. Without using shared secrets to establish authenticated channels, such attacks are notoriously difficult to thwart and can undermine the authentication and key establishment processes. VERSE exploits the existence of multiple devices to verify the integrity of the messages exchanged within the group. We then use VERSE to build a bootstrapping protocol, which securely introduces new devices to the network. Compared to the state-of-the-art, VERSE achieves in-band message integrity verification during secure pairing using only the RF modality without relying on out-of-band channels or extensive human involvement. It guarantees security even when the adversary is capable of fully controlling the wireless channel by annihilating and injecting wireless signals. We study the limits of such advanced wireless attacks and prove that the introduction of multiple legitimate devices can be leveraged to increase the security of the pairing process. We validate our claims via theoretical analysis and extensive experimentations on the USRP platform. We further discuss various implementation aspects such as the effect of time synchronization between devices and the effects of multipath and interference. Note that the elimination of shared secrets, default passwords, and public key infrastructures effectively addresses the related key management challenges when these are considered at scale.
Lewis, Matt.  2018.  Using Graph Databases to Assess the Security of Thingernets Based on the Thingabilities and Thingertivity of Things. Living in the Internet of Things: Cybersecurity of the IoT - 2018. :1-9.

Security within the IoT is currently below par. Common security issues include IoT device vendors not following security best practices and/or omitting crucial security controls and features within their devices, lack of defined and mandated IoT security standards, default IoT device configurations, missing secure update mechanisms to rectify security flaws discovered in IoT devices and the overall unintended consequence of complexity - the attack surface of networks comprising IoT devices can increase exponentially with the addition of each new device. In this paper we set out an approach using graphs and graph databases to understand IoT network complexity and the impact that different devices and their profiles have on the overall security of the underlying network and its associated data.

Bugeja, Joseph, Vogel, Bahtijar, Jacobsson, Andreas, Varshney, Rimpu.  2019.  IoTSM: An End-to-End Security Model for IoT Ecosystems. 2019 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops). :267-272.

The Internet of Things (IoT) market is growing rapidly, allowing continuous evolution of new technologies. Alongside this development, most IoT devices are easy to compromise, as security is often not a prioritized characteristic. This paper proposes a novel IoT Security Model (IoTSM) that can be used by organizations to formulate and implement a strategy for developing end-to-end IoT security. IoTSM is grounded by the Software Assurance Maturity Model (SAMM) framework, however it expands it with new security practices and empirical data gathered from IoT practitioners. Moreover, we generalize the model into a conceptual framework. This approach allows the formal analysis for security in general and evaluates an organization's security practices. Overall, our proposed approach can help researchers, practitioners, and IoT organizations, to discourse about IoT security from an end-to-end perspective.

Blanquer, Ignacio, Meira, Wagner.  2018.  EUBra-BIGSEA, A Cloud-Centric Big Data Scientific Research Platform. 2018 48th Annual IEEE/IFIP International Conference on Dependable Systems and Networks Workshops (DSN-W). :47–48.
This paper describes the achievements of project EUBra-BIGSEA, which has delivered programming models and data analytics tools for the development of distributed Big Data applications. As framework components, multiple data models are supported (e.g. data streams, multidimensional data, etc.) and efficient mechanisms to ensure privacy and security, on top of a QoS-aware layer for the smart and rapid provisioning of resources in a cloud-based environment.
Huang, Jingwei.  2018.  From Big Data to Knowledge: Issues of Provenance, Trust, and Scientific Computing Integrity. 2018 IEEE International Conference on Big Data (Big Data). :2197–2205.
This paper addresses the nature of data and knowledge, the relation between them, the variety of views as a characteristic of Big Data regarding that data may come from many different sources/views from different viewpoints, and the associated essential issues of data provenance, knowledge provenance, scientific computing integrity, and trust in the data science process. Towards the direction of data-intensive science and engineering, it is of paramount importance to ensure Scientific Computing Integrity (SCI). A failure of SCI may be caused by malicious attacks, natural environmental changes, faults of scientists, operations mistakes, faults of supporting systems, faults of processes, and errors in the data or theories on which a research relies. The complexity of scientific workflows and large provenance graphs as well as various causes for SCI failures make ensuring SCI extremely difficult. Provenance and trust play critical role in evaluating SCI. This paper reports our progress in building a model for provenance-based trust reasoning about SCI.
Ali, Abdullah Ahmed, Zamri Murah, Mohd.  2018.  Security Assessment of Libyan Government Websites. 2018 Cyber Resilience Conference (CRC). :1-4.

Many governments organizations in Libya have started transferring traditional government services to e-government. These e-services will benefit a wide range of public. However, deployment of e-government bring many new security issues. Attackers would take advantages of vulnerabilities in these e-services and would conduct cyber attacks that would result in data loss, services interruptions, privacy loss, financial loss, and other significant loss. The number of vulnerabilities in e-services have increase due to the complexity of the e-services system, a lack of secure programming practices, miss-configuration of systems and web applications vulnerabilities, or not staying up-to-date with security patches. Unfortunately, there is a lack of study being done to assess the current security level of Libyan government websites. Therefore, this study aims to assess the current security of 16 Libyan government websites using penetration testing framework. In this assessment, no exploits were committed or tried on the websites. In penetration testing framework (pen test), there are four main phases: Reconnaissance, Scanning, Enumeration, Vulnerability Assessment and, SSL encryption evaluation. The aim of a security assessment is to discover vulnerabilities that could be exploited by attackers. We also conducted a Content Analysis phase for all websites. In this phase, we searched for security and privacy policies implementation information on the government websites. The aim is to determine whether the websites are aware of current accepted standard for security and privacy. From our security assessment results of 16 Libyan government websites, we compared the websites based on the number of vulnerabilities found and the level of security policies. We only found 9 websites with high and medium vulnerabilities. Many of these vulnerabilities are due to outdated software and systems, miss-configuration of systems and not applying the latest security patches. These vulnerabilities could be used by cyber hackers to attack the systems and caused damages to the systems. Also, we found 5 websites didn't implement any SSL encryption for data transactions. Lastly, only 2 websites have published security and privacy policies on their websites. This seems to indicate that these websites were not concerned with current standard in security and privacy. Finally, we classify the 16 websites into 4 safety categories: highly unsafe, unsafe, somewhat unsafe and safe. We found only 1 website with a highly unsafe ranking. Based on our finding, we concluded that the security level of the Libyan government websites are adequate, but can be further improved. However, immediate actions need to be taken to mitigate possible cyber attacks by fixing the vulnerabilities and implementing SSL encryption. Also, the websites need to publish their security and privacy policy so the users could trust their websites.

Zieger, Andrej, Freiling, Felix, Kossakowski, Klaus-Peter.  2018.  The $\beta$-Time-to-Compromise Metric for Practical Cyber Security Risk Estimation. 2018 11th International Conference on IT Security Incident Management IT Forensics (IMF). :115-133.

To manage cybersecurity risks in practice, a simple yet effective method to assess suchs risks for individual systems is needed. With time-to-compromise (TTC), McQueen et al. (2005) introduced such a metric that measures the expected time that a system remains uncompromised given a specific threat landscape. Unlike other approaches that require complex system modeling to proceed, TTC combines simplicity with expressiveness and therefore has evolved into one of the most successful cybersecurity metrics in practice. We revisit TTC and identify several mathematical and methodological shortcomings which we address by embedding all aspects of the metric into the continuous domain and the possibility to incorporate information about vulnerability characteristics and other cyber threat intelligence into the model. We propose $\beta$-TTC, a formal extension of TTC which includes information from CVSS vectors as well as a continuous attacker skill based on a $\beta$-distribution. We show that our new metric (1) remains simple enough for practical use and (2) gives more realistic predictions than the original TTC by using data from a modern and productively used vulnerability database of a national CERT.

Hagan, Matthew, Siddiqui, Fahad, Sezer, Sakir.  2018.  Policy-Based Security Modelling and Enforcement Approach for Emerging Embedded Architectures. 2018 31st IEEE International System-on-Chip Conference (SOCC). :84–89.
Complex embedded systems often contain hard to find vulnerabilities which, when exploited, have potential to cause severe damage to the operating environment and the user. Given that threats and vulnerabilities can exist within any layer of the complex eco-system, OEMs face a major challenge to ensure security throughout the device life-cycle To lower the potential risk and damage that vulnerabilities may cause, OEMs typically perform application threat analysis and security modelling. This process typically provides a high level guideline to solving security problems which can then be implemented during design and development. However, this concept presents issues where new threats or unknown vulnerability has been discovered. To address this issue, we propose a policy-based security modelling approach, which utilises a configurable policy engine to apply new policies that counter serious threats. By utilising this approach, the traditional security modelling approaches can be enhanced and the consequences of a new threat greatly reduced. We present a realistic use case of connected car, applying several attack scenarios. By utilising STRIDE threat modelling and DREAD risk assessment model, adequate policies are derived to protect the car assets. This approach poses advantages over the standard approach, allowing a policy update to counter a new threat, which may have otherwise required a product redesign to alleviate the issue under the traditional approach.
Deb Nath, Atul Prasad, Bhunia, Swarup, Ray, Sandip.  2018.  ArtiFact: Architecture and CAD Flow for Efficient Formal Verification of SoC Security Policies. 2018 IEEE Computer Society Annual Symposium on VLSI (ISVLSI). :411–416.
Verification of security policies represents one of the most critical, complex, and expensive steps of modern SoC design validation. SoC security policies are typically implemented as part of functional design flow, with a diverse set of protection mechanisms sprinkled across various IP blocks. An obvious upshot is that their verification requires comprehension and analysis of the entire system, representing a scalability bottleneck for verification tools. The scale and complexity of industrial SoC is far beyond the analysis capacity of state-of-the-art formal tools; even simulation-based security verification is severely limited in effectiveness because of the need to exercise subtle corner-cases across the entire system. We address this challenge by developing a novel security architecture that accounts for verification needs from the ground up. Our framework, ArtiFact, provides an alternative architecture for security policy implementation that exploits a flexible, centralized, infrastructure IP and enables scalable, streamlined verification of these policies. With our architecture, verification of system-level security policies reduces to analysis of this single IP and its interfaces, enabling off-the-shelf formal tools to successfully verify these policies. We introduce a CAD flow that supports both formal and dynamic (simulation-based) verification, and is built on top of such off-the-shelf tools. Our approach reduces verification time by over 62X and bug detection time by 34X for illustrative policies.
Alzahrani, Ahmed, Johnson, Chris, Altamimi, Saad.  2018.  Information security policy compliance: Investigating the role of intrinsic motivation towards policy compliance in the organisation. 2018 4th International Conference on Information Management (ICIM). :125–132.
Recent behavioral research in information security has focused on increasing employees' motivation to enhance the security performance in an organization. This empirical study investigated employees' information security policy (ISP) compliance intentions using self-determination theory (SDT). Relevant hypotheses were developed to test the proposed research model. Data obtained via a survey (N=3D407) from a Fortune 600 organization in Saudi Arabia provides empirical support for the model. The results confirmed that autonomy, competence and the concept of relatedness all positively affect employees' intentions to comply. The variable 'perceived value congruence' had a negative effect on ISP compliance intentions, and the perceived legitimacy construct did not affect employees' intentions. In general, the findings of this study suggest that SDT has value in research into employees' ISP compliance intentions.
Li, Ling, An, Xiaoguang.  2018.  Research on Storage Mechanism of Cloud Security Policy. 2018 International Conference on Virtual Reality and Intelligent Systems (ICVRIS). :130–133.
Cloud computing, cloud security and cloud storage have been gradually introduced into people's life and become hot topicsof research, for which relevant technologies have permeated through the computer industry and relevant industries. With the coming of the modern information society, secure storage of data has been becoming increasingly important. Proceeding from traditional policy storage, this paper includes comparison and improvement of policy storage for the purpose of meeting requirements of storage of cloud security policy. Policy storage technology refers to a technology used to realize storage of policies created by users and relevant policy information. Policy repository can conduct centralized management and processing of multiple policies and their relevant information. At present, popular policy repositories generally include policy storage for relational database or policy storage for directory server or a file in a fixed format, such as XML file format.
Pan, Y., He, F., Yu, H..  2018.  An Adaptive Method to Learn Directive Trust Strength for Trust-Aware Recommender Systems. 2018 IEEE 22nd International Conference on Computer Supported Cooperative Work in Design ((CSCWD)). :10–16.

Trust Relationships have shown great potential to improve recommendation quality, especially for cold start and sparse users. Since each user trust their friends in different degrees, there are numbers of works been proposed to take Trust Strength into account for recommender systems. However, these methods ignore the information of trust directions between users. In this paper, we propose a novel method to adaptively learn directive trust strength to improve trust-aware recommender systems. Advancing previous works, we propose to establish direction of trust strength by modeling the implicit relationships between users with roles of trusters and trustees. Specially, under new trust strength with directions, how to compute the directive trust strength is becoming a new challenge. Therefore, we present a novel method to adaptively learn directive trust strengths in a unified framework by enforcing the trust strength into range of [0, 1] through a mapping function. Our experiments on Epinions and Ciao datasets demonstrate that the proposed algorithm can effectively outperform several state-of-art algorithms on both MAE and RMSE metrics.

Coleman, M. S., Doody, D. P., Shields, M. A..  2018.  Machine Learning for Real-Time Data-Driven Security Practices. 2018 29th Irish Signals and Systems Conference (ISSC). :1–6.

The risk of cyber-attacks exploiting vulnerable organisations has increased significantly over the past several years. These attacks may combine to exploit a vulnerability breach within a system's protection strategy, which has the potential for loss, damage or destruction of assets. Consequently, every vulnerability has an accompanying risk, which is defined as the "intersection of assets, threats, and vulnerabilities" [1]. This research project aims to experimentally compare the similarity-based ranking of cyber security information utilising a recommendation environment. The Memory-Based Collaborative Filtering technique was employed, specifically the User-Based and Item-Based approaches. These systems utilised information from the National Vulnerability Database, specifically for the identification and similarity-based ranking of cyber-security vulnerability information, relating to hardware and software applications. Experiments were performed using the Item-Based technique, to identify the optimum system parameters, evaluated through the AUC evaluation metric. Once identified, the Item-Based technique was compared with the User-Based technique which utilised the parameters identified from the previous experiments. During these experiments, the Pearson's Correlation Coefficient and the Cosine similarity measure was used. From these experiments, it was identified that utilised the Item-Based technique which employed the Cosine similarity measure, an AUC evaluation metric of 0.80225 was achieved.

Qi, L. T., Huang, H. P., Wang, P., Wang, R. C..  2018.  Abnormal Item Detection Based on Time Window Merging for Recommender Systems. 2018 17th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/ 12th IEEE International Conference On Big Data Science And Engineering (TrustCom/BigDataSE). :252–259.

CFRS (Collaborative Filtering Recommendation System) is one of the most widely used individualized recommendation systems. However, CFRS is susceptible to shilling attacks based on profile injection. The current research on shilling attack mainly focuses on the recognition of false user profiles, but these methods depend on the specific attack models and the computational cost is huge. From the view of item, some abnormal item detection methods are proposed which are independent of attack models and overcome the defects of user profiles model, but its detection rate, false alarm rate and time overhead need to be further improved. In order to solve these problems, it proposes an abnormal item detection method based on time window merging. This method first uses the small window to partition rating time series, and determine whether the window is suspicious in terms of the number of abnormal ratings within it. Then, the suspicious small windows are merged to form suspicious intervals. We use the rating distribution characteristics RAR (Ratio of Abnormal Rating), ATIAR (Average Time Interval of Abnormal Rating), DAR(Deviation of Abnormal Rating) and DTIAR (Deviation of Time Interval of Abnormal Rating) in the suspicious intervals to determine whether the item is subject to attacks. Experiment results on the MovieLens 100K data set show that the method has a high detection rate and a low false alarm rate.

Panagiotakis, C., Papadakis, H., Fragopoulou, P..  2018.  Detection of Hurriedly Created Abnormal Profiles in Recommender Systems. 2018 International Conference on Intelligent Systems (IS). :499–506.

Recommender systems try to predict the preferences of users for specific items. These systems suffer from profile injection attacks, where the attackers have some prior knowledge of the system ratings and their goal is to promote or demote a particular item introducing abnormal (anomalous) ratings. The detection of both cases is a challenging problem. In this paper, we propose a framework to spot anomalous rating profiles (outliers), where the outliers hurriedly create a profile that injects into the system either random ratings or specific ratings, without any prior knowledge of the existing ratings. The proposed detection method is based on the unpredictable behavior of the outliers in a validation set, on the user-item rating matrix and on the similarity between users. The proposed system is totally unsupervised, and in the last step it uses the k-means clustering method automatically spotting the spurious profiles. For the cases where labeling sample data is available, a random forest classifier is trained to show how supervised methods outperforms unsupervised ones. Experimental results on the MovieLens 100k and the MovieLens 1M datasets demonstrate the high performance of the proposed schemata.