Several high-ranking watermarking schemes using neural networks have been proposed in order to make the watermark stronger to resist attacks. The ability of Artificial Neural Network, ANN to learn, do mapping, classify, and adapt has increased the interest of researcher in application of different types ANN in watermarking. In this paper, ANN based approached have been categorized based on their application to different components of watermarking such as; capacity estimate, watermark embedding, recovery of watermark and error rate detection. We propose a new component of water marking, Secure Region, SR in which, ANN can be used to identify such region within the estimated capacity. Hence an attack-proof watermarking system can be achieved.
This paper discusses the proposed system which provides the user the ability to run the application on Android phones for encrypting all types of files before they are stored. Methods/Statistical Analysis: In the proposed system, Advanced Encryption Standard (AES) is employed for encryption as well as decryption of the files stored by users in mobile phones. All types of files including docx, text, pdf, image, ppt, audio and video files can be encrypted and later regenerated as well. Findings: The use of AES in encrypting and decrypting data in this system provides good security as well as higher speed. An added advantage is that it is implementable on several platforms particularly in small gadgets like smartphones. As compared to the traditional computers, smartphones can be carried more easily and provide similar functionalities as that of a computer like data storage and processing, communication and other services including video call, wireless network, web browser, GPS, audio or video player. Application/Improvements: Data is transmitted, shared and stored for various purposes including production, banking, development, and research. Therefore, security is a must for information which can be provided by encryption using AES as proposed in this system.
In this paper, an approach to online banking authorization using one-time passwords has been illustrated. Methods/Statistical Analysis: The algorithm presented in this paper provides an infinite as well as forward One-Time- Password (OTP) generation mechanism employing two Secure Hash Algorithms viz. SHA3 and SHA2, followed by dynamic truncation to produce human-readable OTP. An inimitable authentication scheme has been presented in which a unique initial seed is used for generating a series of OTPs on the user’s handheld gadget (i.e. a mobile phone). Findings: The proposed scheme demonstrated better results than the previous schemes of authorization after a security analysis was conducted on it. This is attributed to the eradication of cellular network within the authorization process. A high level of performance and efficiency in authentication and authorization was evident from the results that are vital for transacting online. Applications/Improvements: In the proposed system, the inherent features of the user’s device (mobile phone) are utilized to form the initial seed. The application of hash functions to that seed eliminates the necessity to send one time passwords to the users via Short Message Service and decreases the limitations posed by out-of-band systems, thus making it suitable to be employed in online banking and other financial organizations.
In this paper, a smart Intrusion Detection System (IDS) has been proposed that detects network attacks in less time after monitoring incoming traffic thus maintaining better performance. Methods/Statistical Analysis: The features are extracted using back-propagation algorithm. Then, only these relevant features are trained with the help of multi-layer perceptron supervised neural network. The simulation is performed using MATLAB. Findings: The proposed system has been verified to have high accuracy rate, high sensitivity as well as a reduction in false positive rate. Besides, the intrusions have been classified into four categories as Denial-of-Service (DoS), User-to-root (U2R), Remote-to-Local (R2L) and Probe attacks; and the alerts are stored and shared via a central log. Thus, the unknown attacks detected by other Intrusion Detection Systems can be sensed by any IDS in the network thereby reducing computational cost as well as enhancing the overall detection rate. Applications/Improvements: The proposed system does not waste time by considering and analysing all the features but takes into consideration only relevant ones for the specific attack and supervised learning neural network is used for intrusion detection. By the application of Snort before backpropagation algorithm, the latter has only one function to perform – detection of unknown attacks. In this way, the time for attack detection is reduced.
The increased usage of World Wide Web leads to increase in network traffic and create a bottleneck over the internet performance. For most people, the accessing speed or the response time is the most critical factor when using the internet. Reducing response time was done by using web proxy cache technique that storing a copy of pages between client and server sides. If requested pages are cached in the proxy, there is no need to access the server. But, the cache size is limited, so cache replacement algorithms are used to remove pages from the cache when it is full. On the other hand, the conventional algorithms for replacement such as Least Recently Use (LRU), First in First Out (FIFO), Least Frequently Use (LFU), Randomised Policy, etc. may discard essential pages just before use. Furthermore, using conventional algorithms cannot be well optimized since it requires some decision to evict intelligently before a page is replaced. Hence, this paper proposes an integration of Adaptive Weight Ranking Policy (AWRP) with intelligent classifiers (NB-AWRP-DA and J48-AWRP-DA) via dynamic aging factor. To enhance classifiers power of prediction before integrating them with AWRP, particle swarm optimization (PSO) automated wrapper feature selection methods are used to choose the best subset of features that are relevant and influence classifiers prediction accuracy. Experimental Result shows that NB-AWRP-DA enhances the performance of web proxy cache across multi proxy datasets by 4.008%,4.087% and 14.022% over LRU, LFU, and FIFO while, J48-AWRP-DA increases HR by 0.483%, 0.563% and 10.497% over LRU, LFU, and FIFO respectively. Meanwhile, BHR of NB-AWRP-DA rises by 0.9911%,1.008% and 11.5842% over LRU, LFU, and FIFO respectively while 0.0204%, 0.0379% and 10.6136 for LRU, LFU, FIFO respectively using J48-AWRP-DA.