Remote authentication via biometrics: a robust video-object steganographic mechanism over wireless networks
Journal
IEEE Transactions on Emerging Topics in Computing
Date Issued
February 18, 2015
Author(s)
DOI
10.1109/TETC.2015.2400135
Abstract
In wireless communications sensitive information is
frequently exchanged, requiring remote authentication. Remote
authentication involves the submission of encrypted information,
along with visual and audio cues (facial images/videos, human
voice etc.). Nevertheless, Trojan Horse and other attacks can
cause serious problems, especially in cases of remote examinations
(in remote studying) or interviewing (for personnel hiring). This
paper proposes a robust authentication mechanism based on
semantic segmentation, chaotic encryption and data hiding. Assuming
that user X wants to be remotely authenticated, initially
X’s video object (VO) is automatically segmented, using a headand-body
detector. Next, one of X’s biometric signals is encrypted
by a chaotic cipher. Afterwards the encrypted signal is inserted to
the most significant wavelet coefficients of the VO, using its Qualified
Significant Wavelet Trees (QSWTs). QSWTs provide both
invisibility and significant resistance against lossy transmission
and compression, conditions that are typical in wireless networks.
Finally, the Inverse Discrete Wavelet Transform (IDWT) is
applied to provide the stego-object (SO). Experimental results,
regarding: (a) security merits of the proposed encryption scheme,
(b) robustness to steganalytic attacks, to various transmission
losses and JPEG compression ratios and (c) bandwidth efficiency
measures, indicate the promising performance of the proposed
biometrics-based authentication scheme.
frequently exchanged, requiring remote authentication. Remote
authentication involves the submission of encrypted information,
along with visual and audio cues (facial images/videos, human
voice etc.). Nevertheless, Trojan Horse and other attacks can
cause serious problems, especially in cases of remote examinations
(in remote studying) or interviewing (for personnel hiring). This
paper proposes a robust authentication mechanism based on
semantic segmentation, chaotic encryption and data hiding. Assuming
that user X wants to be remotely authenticated, initially
X’s video object (VO) is automatically segmented, using a headand-body
detector. Next, one of X’s biometric signals is encrypted
by a chaotic cipher. Afterwards the encrypted signal is inserted to
the most significant wavelet coefficients of the VO, using its Qualified
Significant Wavelet Trees (QSWTs). QSWTs provide both
invisibility and significant resistance against lossy transmission
and compression, conditions that are typical in wireless networks.
Finally, the Inverse Discrete Wavelet Transform (IDWT) is
applied to provide the stego-object (SO). Experimental results,
regarding: (a) security merits of the proposed encryption scheme,
(b) robustness to steganalytic attacks, to various transmission
losses and JPEG compression ratios and (c) bandwidth efficiency
measures, indicate the promising performance of the proposed
biometrics-based authentication scheme.