Enhanced Rsa (Ersa): An Advanced Mechanism for Improving the Security

Cloud computing has become ubiquitous in our daily lives in recent years.Data are the source of technology that is generated hugely by various sources.Big data is dealing with huge data volumes or complex data.The major concern in big data is security threats.Security concerns create a negative impact on the user on the aspect of trust.In big data still,security threats exist as com-monly known as DDOS(Distributed-Denial-of-Service)attacks,data loss,Inade-quate Data Backups,System Vulnerabilities,and Phishing as well as Social Engineering Attacks.In our work,we have taken the data loss and Inadequate Data Backups issues into consideration.We analyze that RSA(Rivest,Shamir,&Adleman)is the most secure cryptography mechanism.In cloud computing,user authentication is the weaker section to be secured.Generally,the cryptogra-phy mechanism is done in the authentication section only.We implemented our new idea of registration with selected images and pins for processing RSA.By valid authentication approval earned by the proposed mechanism,the user is allowed to use the cloud database,encryption,decryption,etc.To prove the effi-ciency level of our proposed system,a comparison work is conducted between DSSE(Digital Signature Standard Encryption)and EFSSA(Efficient framework for securely sharing afile using asymmetric key distribution management).The experimental work is carried out and the performance evaluation is done using encryption time and decryption time analysis,throughput,and processing time.On this observation,the security level attained by ERSA is far better in compar-ison to DSSE and EFSSA with the maximum throughput attained by the proposed E-RSA being 500 Mb/Min and encryption time of 3.2 s,thus ensuring the user trust in using the cloud environment.

Performance Analysis of Hybrid RR Algorithm for Anomaly Detection in Streaming Data

Automated live video stream analytics has been extensively researched in recent times.Most of the traditional methods for video anomaly detection is supervised and use a single classifier to identify an anomaly in a frame.We propose a 3-stage ensemble-based unsupervised deep reinforcement algorithm with an underlying Long Short Term Memory(LSTM)based Recurrent Neural Network(RNN).In the first stage,an ensemble of LSTM-RNNs are deployed to generate the anomaly score.The second stage uses the least square method for optimal anomaly score generation.The third stage adopts award-based reinforcement learning to update the model.The proposed Hybrid Ensemble RR Model was tested on standard pedestrian datasets UCSDPed1,USDPed2.The data set has 70 videos in UCSD Ped1 and 28 videos in UCSD Ped2 with a total of 18560 frames.Since a real-time stream has strict memory constraints and storage issues,a simple computing machine does not suffice in performing analytics with stream data.Hence the proposed research is designed to work on a GPU(Graphics Processing Unit),TPU(Tensor Processing Unit)supported framework.As shown in the experimental results section,recorded observations on framelevel EER(Equal Error Rate)and AUC(Area Under Curve)showed a 9%reduction in EER in UCSD Ped1,a 13%reduction in ERR in UCSD Ped2 and a 4%improvement in accuracy in both datasets.