This is the accepted version of the paper.This version of the publication may differ from the final published version. Abstract-Emerging cloud computing infrastructure replaces traditional outsourcing techniques and provides flexible services to clients at different locations via Internet. This leads to the requirement for data classification to be performed by potentially untrusted servers in the cloud. Within this context, classifier built by the server can be utilized by clients in order to classify their own data samples over the cloud. In this paper, we study a privacy-preserving (PP) data classification technique where the server is unable to learn any knowledge about clients' input data samples while the server side classifier is also kept secret from the clients during the classification process. More specifically, to the best of our knowledge, we propose the first known client-server data classification protocol using support vector machine. The proposed protocol performs PP classification for both two-class and multi-class problems. The protocol exploits properties of Pailler homomorphic encryption and secure two-party computation. At the core of our protocol lies an efficient, novel protocol for securely obtaining the sign of Pailler encrypted numbers. Permanent repository link

This is the unspecified version of the paper.This version of the publication may differ from the final published version. Abstract-A clinical decision support system forms a critical capability to link health observations with health knowledge to influence choices by clinicians for improved healthcare. Recent trends towards remote outsourcing can be exploited to provide efficient and accurate clinical decision support in healthcare. In this scenario, clinicians can use the health knowledge located in remote servers via the Internet to diagnose their patients. However, the fact that these servers are third party and therefore potentially not fully trusted raises possible privacy concerns. In this paper, we propose a novel privacy-preserving protocol for a clinical decision support system where the patients' data always remain in encrypted form during the diagnosis process. Hence the server involved in the diagnosis process is not able to learn any extra knowledge about the patient data and results. Our experimental results on popular medical data sets from UCI database demonstrate that the accuracy of the proposed protocol is up to 97.21% and the privacy of patient data is not compromised. Permanent repository link

This is the accepted version of the paper.This version of the publication may differ from the final published version. Abstract-Decentralized attribute-based encryption (ABE) is a variant of multi-authority based ABE whereby any attribute authority (AA) can independently join and leave the system without collaborating with the existing AAs. In this paper, we propose a user collusion avoidance scheme which preserves the user's privacy when they interact with multiple authorities to obtain decryption credentials. The proposed scheme mitigates the well-known user collusion security vulnerability found in previous schemes. We show that our scheme relies on the standard complexity assumption (decisional bilienar Deffie-Hellman assumption). This is contrast to previous schemes which relies on non-standard assumption (q-decisional Diffie-Hellman inversion). PermanentIndex Terms-Attribute-based encryption, user collusion.

Volume anomaly such as distributed denial-of-service (DDoS) has been around for ages but with advancement in technologies, they have become stronger, shorter and weapon of choice for attackers. Digital forensic analysis of intrusions using alerts generated by existing intrusion detection system (IDS) faces major challenges, especially for IDS deployed in large networks. In this paper, the concept of automatically sifting through a huge volume of alerts to distinguish the different stages of a DDoS attack is developed. The proposed novel framework is purposebuilt to analyze multiple logs from the network for proactive forecast and timely detection of DDoS attacks, through a combined approach of Shannon-entropy concept and clustering algorithm of relevant feature variables. Experimental studies on a cyber-range simulation dataset from the project industrial partners show that the technique is able to distinguish precursor alerts for DDoS attacks, as well as the attack itself with a very low false positive rate (FPR) of 22.5%. Application of this technique greatly assists security experts in network analysis to combat DDoS attacks. Index Terms-alert management, distributed denial-of-service (DDoS) detection, k-means clustering analysis, network security, online anomaly detection, Shannon entropy.

Distributed denial of service (DDoS) attacks continues to grow as a threat to organizations worldwide. From the first known attack in 1999 to the highly publicized Operation Ababil, the DDoS attacks have a history of flooding the victim network with an enormous number of packets, hence exhausting the resources and preventing the legitimate users to access them. After having standard DDoS defense mechanism, still attackers are able to launch an attack. These inadequate defense mechanisms need to be improved and integrated with other solutions. The purpose of this paper is to study the characteristics of DDoS attacks, various models involved in attacks and to provide a timeline of defense mechanism with their improvements to combat DDoS attacks. In addition to this, a novel scheme is proposed to detect DDoS attack efficiently by using MapReduce programming model.

No abstract

This is the unspecified version of the paper.This version of the publication may differ from the final published version. Abstract-Surname (family name) analysis is used in geography to understand population origins, migration, identity, social norms and cultural customs. Some of these are supposedly evolved over generations. Surnames exhibit good statistical properties that can be used to extract information in names data set such as automatic detection of ethnic or community groups in names. An e-mail address, often contains surname as a substring. This containment may be full or partial. An e-mail address categorization based on semantics of surnames is the objective of this paper. This is achieved in two phases. First phase deals with surname representation and clustering. Here, a vector space model is proposed where latent semantic analysis is performed. Clustering is done using the method called averagelinkage method. In the second phase, an email is categorized as belonging to one of the categories (discovered in first phase). For this, substring matching is required, which is done in an efficient way by using suffix tree data structure. We perform experimental evaluation for the 500 most frequently occurring surnames in India and United Kingdom. Also, we categorize the e-mail addresses that have these surnames as substrings. Permanent repository link

Optimal resource utilization is one of the biggest challenges for executing tasks within the cloud. The resource provider is responsible for providing the resources by creating virtual machines for executing task over a cloud. To utilize the resources optimally, the resource provider has to take care of the process of allocating resources to Virtual Machine Manager (VMM). In this paper, an efficient way to utilize the resources, within the cloud, has been proposed considering remaining resources should be maximum at a single machine but not distributed. As a framework to virtual resource mapping, a Simple Genetic Algorithm is applied to solve the heuristic of allocating problem. We may also use conversion of multiple parameters into single equivalent parameter so that number of inputs and comparisons will be reduced.