Ensuring confidentiality and integrity of multimedia data on multi-core platforms

Authors:
Eunji Lee;Sungju Lee;Yongwha Chung;Hyeonjoong Cho;Sung Bum Pan
Affiliations:
Department of Computer and Information Science, Korea University, Korea;Department of Computer and Information Science, Korea University, Korea;Department of Computer and Information Science, Korea University, Korea;Department of Computer and Information Science, Korea University, Korea;Dept. of Control, Instrumentation, and Robot Engineering, Chosun Univ., Korea
Venue:
ICA3PP'10 Proceedings of the 10th international conference on Algorithms and Architectures for Parallel Processing - Volume Part II
Year:
2010

Citing 5
Cited 0

MPEG Handbook

MPEG Handbook
Video compression with parallel processing

Parallel Computing - Parallel computing in image and video processing
On the Security of CTR + CBC-MAC

SAC '02 Revised Papers from the 9th Annual International Workshop on Selected Areas in Cryptography
Multimedia Security Handbook

Multimedia Security Handbook
SP 800-38C. Recommendation for Block Cipher Modes of Operation: the CCM Mode for Authentication and Confidentiality

SP 800-38C. Recommendation for Block Cipher Modes of Operation: the CCM Mode for Authentication and Confidentiality

Quantified Score

Hi-index	0.00

Visualization

Abstract

SECMPEG selectively encrypts data to protect MPEG video streams with minimum overhead. However, this scheme is known to provide only confidentiality but not integrity for data. In this paper, we apply AES-CCM to SECMPEG for ensuring integrity as well as confidentiality for multimedia data. Furthermore, in order to satisfy the real-time requirement, we use a multi-core processor. After analyzing the computational characteristics of SECMPEG/AES-CCM on a multi-core processor, we parallelize SECMPEG/AES-CCM with both static and dynamic task assignments. Our experimental results show that a near-optimal speed-up could be obtained using on 4-core processor with ensuring both confidentiality and integrity of multimedia data.