Loading...

Physical Layer Secure Image Transmission Based on Machine Learning Methods

Letafati, Mehdi | 2021

500 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 54417 (05)
  4. University: Sharif University of Technology
  5. Department: Electrical Engineering
  6. Advisor(s): Behroozi, Hamid; Hossein Khalaj, Babak
  7. Abstract:
  8. The rapid development of wireless communications, e.g., the sixth generation (6G) networks, together with the emergence of various technologies for exchanging data has made the information security a big concern. In other words, today’s decentralized wireless networks face with major challenges in terms of key distribution and management of traditional cryptographic techniques. In contrast, the approach of PHY layer security, which wisely utilizes the inherent characteristics of wireless links, has been introduced to address provable and lightweight security mechanisms. In addition, learning-based techniques have shown to be able to provide well-established mechanisms in enhancing the performance of systems with security requirements. In this thesis, we investigate the problem of secure image transmission in the presence of totally-passive randomly-located eavesdroppers. By utilizing a learning-based approach towards PHY security, we propose a content- and latency- aware secure image transmission scheme. In our proposed system, a multi-antenna source should securely deliver image packets to the legitimate destination while con- forming to the tolerable delay limits. We take into account the fact that not all regions of an image have the same importance from the security perspective. Thus, different strategies are adopted to deal with different segments of image. The secrecy performance of our scheme is characterized by deriving a closed-form expression for the quality-of-security (QoSec) violation probability. Our proposed image delivery scheme leverages a deep neural network (DNN) and learns to maintain optimized transmission parameters, while minimizing the QoSec violation probability. Simulation results are provided to illustrate that our proposed learning-assisted scheme outperforms the state-of-the-arts by achieving considerable gains in terms of security and delay requirement
  9. Keywords:
  10. Machine Learning ; Physical Layer Security ; Wireless Networks ; Information Security ; Wireless Communication ; Content Aware Algorithm ; Secure Image Transmission

 Digital Object List

 Bookmark

...see more