Abstract : In the last decade, the benefit of online payment has opened several new opportunities for e-commerce, lowering the geographical boundaries for retail. While e-commerce continues to be gaining quality, it's additionally the playground of fraudsters UN agency try to misuse the transparency of online purchases and also the transfer of master-card records. We establish GOTCHA! A new method on how to describe and take out features from a time-weighted network, and how to develop and integrate network-based and intrinsic quality in fraud detection (FD). The grouping of all features (i.e., intrinsic and network features) is fed to the machine learning methods. This is the Gotcha! Model. As the formation of network features drastically increases the number of features to learn from, all together methods like Random Forest are used to train the models. Keywords : OTB, FD, Gotcha, Dot-NetB(DN).
Authors - ReshmaChandran, R Usha Nandhini, J.R.Nishanth, J Jarin Joe Rini
Abstract : With the spread of digital data around the world through the internet, the security of the data has raised a concern to the people. Many methods are coming up to protect the data from going into the hands of the unauthorized person. Steganography and cryptography are two different techniques for data security. The main purpose in cryptography is to make message concept unintelligible, while Steganography aims to hide secret message. Digital images are excellent carriers of hidden information. We propose a method of combining Steganography and cryptography for secret data communication. In this paper, we propose a high-performance JPEG Steganography along with a substitution encryption methodology. The approach uses the discrete cosine transform (DCT) technique which used in the frequency domain for hiding encrypted data within image. Experimental results show that the visual and the statistical values of the image with encrypted data before the insertion are similar to the values after the insertion thus reduces the chance of the confidential message being detected and enables secret communication. The effectiveness of the proposed method has been estimated by computing Mean square error (MSE) and Peak Signal to Noise Ratio (PSNR). Keywords : Steganography, Cryptography, plaintext, encryption, decryption, ciphertext, substitution cipher, discrete cosine transform, JPEG, quantization, Mean square error and Peak Signal to Noise Ratio.