Publication

Abstract : Technology has done a great deal for changing the way we live and do business today. We can see the use of computers from the vegetable shop to large scale businesses. In this fast moving world we need something essential for fast computation. So here comes the Graphics Processing unit for fastest computation through means of its parallel architecture. Along with the popular use of computer, information security has also become one of the problems which need to be solved. Many security issues like the malware authors, information leakage, endan germent and unauthorized exploitation need to be taken into account. To control this, crypto-security is necessary. More Applications started to use Advanced Encryption Standard (AES). However, Since AES on large blocks is computationally intensive and largely byte-parallel. Certain modes of AES are more easily parallelizable and these are ideal candidates for parallelization on GPUs. In this paper, we study the technologies of GPU parallel computing and its optimized design for cryptography. Implementation is done using the CUDA platform. CUDA is a parallel compu ting platform and programming model created by NVIDIA and implemented by the graphics processing units (GPUs) that they produce. The test proves that our approach can accelerate the speed of AES encryption significantly.