Visible to the public Biblio

Filters: Author is Khan, Samee U.  [Clear All Filters]
Al-Odat, Zeyad, Abbas, Assad, Khan, Samee U..  2019.  Randomness Analyses of the Secure Hash Algorithms, SHA-1, SHA-2 and Modified SHA. 2019 International Conference on Frontiers of Information Technology (FIT). :316–3165.
This paper introduces a security analysis scheme for the most famous secure hash algorithms SHA-1 and SHA-2. Both algorithms follow Merkle Damgård structure to compute the corresponding hash function. The randomness of the output hash reflects the strength and security of the generated hash. Therefore, the randomness of the internal rounds of the SHA-1 and SHA-2 hash functions is analyzed using Bayesian and odd ratio tests. Moreover, a proper replacement for both algorithms is proposed, which produces a hash output with more randomness level. The experiments were conducted using a high performance computing testbed and CUDA parallel computing platform.
Yang, Jiannan, Zhang, Fan, Chen, Bike, Khan, Samee U..  2019.  Facial Expression Recognition Based on Facial Action Unit. 2019 Tenth International Green and Sustainable Computing Conference (IGSC). :1—6.

In the past few years, there has been increasing interest in the perception of human expressions and mental states by machines, and Facial Expression Recognition (FER) has attracted increasing attention. Facial Action Unit (AU) is an early proposed method to describe facial muscle movements, which can effectively reflect the changes in people's facial expressions. In this paper, we propose a high-performance facial expression recognition method based on facial action unit, which can run on low-configuration computer and realize video and real-time camera FER. Our method is mainly divided into two parts. In the first part, 68 facial landmarks and image Histograms of Oriented Gradients (HOG) are obtained, and the feature values of action units are calculated accordingly. The second part uses three classification methods to realize the mapping from AUs to FER. We have conducted many experiments on the popular human FER benchmark datasets (CK+ and Oulu CASIA) to demonstrate the effectiveness of our method.

Al-Odat, Zeyad A., Khan, Samee U..  2019.  Anonymous Privacy-Preserving Scheme for Big Data Over the Cloud. 2019 IEEE International Conference on Big Data (Big Data). :5711–5717.
This paper introduces an anonymous privacy-preserving scheme for big data over the cloud. The proposed design helps to enhance the encryption/decryption time of big data by utilizing the MapReduce framework. The Hadoop distributed file system and the secure hash algorithm are employed to provide the anonymity, security and efficiency requirements for the proposed scheme. The experimental results show a significant enhancement in the computational time of data encryption and decryption.
Al-Odat, Zeyad A., Al-Qtiemat, Eman M., Khan, Samee U..  2019.  A Big Data Storage Scheme Based on Distributed Storage Locations and Multiple Authorizations. 2019 IEEE 5th Intl Conference on Big Data Security on Cloud (BigDataSecurity), IEEE Intl Conference on High Performance and Smart Computing, (HPSC) and IEEE Intl Conference on Intelligent Data and Security (IDS). :13—18.

This paper introduces a secured and distributed Big Data storage scheme with multiple authorizations. It divides the Big Data into small chunks and distributes them through multiple Cloud locations. The Shamir's Secret Sharing and Secure Hash Algorithm are employed to provide the security and authenticity of this work. The proposed methodology consists of two phases: the distribution and retrieving phases. The distribution phase comprises three operations of dividing, encrypting, and distribution. The retrieving phase performs collecting and verifying operations. To increase the security level, the encryption key is divided into secret shares using Shamir's Algorithm. Moreover, the Secure Hash Algorithm is used to verify the Big Data after retrieving from the Cloud. The experimental results show that the proposed design can reconstruct a distributed Big Data with good speed while conserving the security and authenticity properties.