Muhammad Amin

Scalable, Privacy-Preserving Remote Attestation in and through Federated Identity Management Frameworks

Creating trustworthy online computing is an important open issue in security research. Trusted Computing aims to address this problem through the use of remote attestation but comes with its own baggage in the form of privacy concerns. Federated Identity Management Systems (FIDMSs), on the other hand, provide another form of trust but lack the ability to measure the integrity of platforms that they vouch for. We note that these two security architectures have reciprocal strengths and weaknesses and can be combined to create an architecture that addresses the concerns of both. In this paper, we propose an extended FIDMS in which the identity provider not only vouches for the identity of a user but also for her platforms integrity. In this way, we (a) allow a service provider to establish trust on a client platforms integrity without sacrificing privacy; and (b) create a feasible and scalable architecture for remote attestation. We describe our proposed architecture in the context of Shibboleth FIDMS and provide the details of the implementation of this system.

DeepSIC: a deep model

Satellite Image Classification is the problem of classifying satellite images into their corresponding classes. Using supervised deep learning, we provide an efficient classification mechanism of earth observation imagery captured by satellite. Promising classification results were obtained through Convolution Neural Network. Two sets of experiments were carried out. In the first set, the traditional pre-deep learning era approach was followed: features were extracted first which were then given as input to Support Vector Machines (SVM). In the second set of experiments, the images were directly provided as input to Convolution Neural Networks and the output features were then used as input to the SVM. The proposed schemes were tested on satellite images datasets AID, UC-merced and WHU-RS, having varied classes and heterogeneous image dimensions. We show that our model, with Convolution Neural Network, achieves 92% accuracy on the AID dataset and outperforms the previously reported best accuracy of 89.64% (Xia et al. in CoRR, arXiv:1608.05167, 2016).

SELinux in and out

Security Enhanced Linux (SELinux) is a widely used Mandatory Access Control system which is integrated in the Linux kernel. It is an added layer of security mechanism on top of the standard Discretionary Access Control system that Unix/Linux and other major operating systems have. SELinux does not nullify DAC but in fact supports DAC and its checks are performed after DACs. If DAC allows an operation then SELinux checks that operation by comparing it with the set of specified rules that it has and decides based on those rules only. If DAC denies some access then SELinux checks are not performed. Because DAC allows users to have full control over files that they own, they could unwantedly set any permission on the files that they own, at their own discretion, which could prove dangerous so for this reason SELinux brings the Mandatory Access Controls (MAC) mechanism which enforces rules based on a specified policy and denies access operations if policy in use do not allow it, even if the file permissions were world-accessible using DAC In this paper we discuss various SELinux policies and provide a statistical comparison using standard Delphi method.

Efficient computational model for classification of protein localization images using Extended Threshold Adjacency Statistics and Support Vector Machines

BACKGROUND AND OBJECTIVE Discriminative and informative feature extraction is the core requirement for accurate and efficient classification of protein subcellular localization images so that drug development could be more effective. The objective of this paper is to propose a novel modification in the Threshold Adjacency Statistics technique and enhance its discriminative power. METHODS In this work, we utilized Threshold Adjacency Statistics from a novel perspective to enhance its discrimination power and efficiency. In this connection, we utilized seven threshold ranges to produce seven distinct feature spaces, which are then used to train seven SVMs. The final prediction is obtained through the majority voting scheme. The proposed ETAS-SubLoc system is tested on two benchmark datasets using 5-fold cross-validation technique. RESULTS We observed that our proposed novel utilization of TAS technique has improved the discriminative power of the classifier. The ETAS-SubLoc system has achieved 99.2% accuracy, 99.3% sensitivity and 99.1% specificity for Endogenous dataset outperforming the classical Threshold Adjacency Statistics technique. Similarly, 91.8% accuracy, 96.3% sensitivity and 91.6% specificity values are achieved for Transfected dataset. CONCLUSIONS Simulation results validated the effectiveness of ETAS-SubLoc that provides superior prediction performance compared to the existing technique. The proposed methodology aims at providing support to pharmaceutical industry as well as research community towards better drug designing and innovation in the fields of bioinformatics and computational biology. The implementation code for replicating the experiments presented in this paper is available at: https://drive.google.com/file/d/0B7IyGPObWbSqRTRMcXI2bG5CZWs/view?usp=sharing.