فهرست مطالب

Journal of Advances in Computer Research
Volume:13 Issue: 1, Winter 2022

  • تاریخ انتشار: 1401/05/01
  • تعداد عناوین: 2
|
  • Masoud Moradi, Masoud Moradkhani, MohammadBagher Tavakoli Pages 1-26

    With the development of IoT, the devices connected to this platform, can exchange data and share their data in social networks. Although this possibility provides advantage, but is has some security challenges like preserving privacy, confidentiality, accessibility, and data integrity in the social networks. In the existing studies, a type of encoding has been used for preserving security. In this paper for improving the security, we introduce a Markov process for describing a security attack model based on Markov transmission matrix. By applying the Markov transmission in blockchain infrastructure we will enhancing security in blockchain‐based social networks. A security threat is a random process. Therefore, we can modelled it as a Markov chain. First the proposed method is compared to SHA1, and results show that the complexity is improved 215% and 240% in terms of hash length, and internal state size, respectively. In this study, nine hash functions, including SHA, four families of SHA2, and four families of SHA3, including SHA3-512, SHA3-384, SHA3-256, and SHA3-224 are simulated ten times. The results indicate a security improvement of 206.59% of SHA3-512 compared to other functions.

    Keywords: IoT, security, blockchain, markov chain, SHA1
  • Behzad Lak, Mojgan Tanbakoosaz Pages 27-37

    With the increasing production of content in today's world, it is becoming more and more important to pay attention to the principles of document summarization that preserve the meaning of the original document. Document summaries are used everywhere today. Ability to summarize faster in publishing documents and content can be effective. These include scientific articles and news sites. Providing a summary system for Persian language that can provide a desirable summary such as transforming unstructured, can be used in various aspects. In this research, an abstract summarization method based on recursive neural networks and the architecture of Long short-term memory (LSTM) networks and the seq2seq model along with the attention mechanism is presented. The evaluation results show that the summary method proposed in this study using the seq2seq model along with the attention mechanism improves the measurement criteria. We compared the presented model with three examples of models presented for English language and also a model presented for Persian language. Rouge criterion was used to measure the quality of model results.

    Keywords: Automatic text summarization, abstract summarization, natural language processing, deep learning, sequence-to-sequence models