An Audio-Visual Imposture Scenario by Talking Face Animation

Karam, Walid; Mokbel, Chafic; Greige, Hanna; Aversano, Guido; Pélachaud, Catherine; Chollet, Gérard

doi:10.1007/11520153_19

Cited by 3 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This technique is reported to have 0.8% equal error rate; the statistical confidence level of this figure is not provided. Karam et al [13] describe a method allowing an impostor to guide, in realtime, the facial movements and speech of a synthetic face With the issuing module, the user reviews and verifies a given av-certificate, records an av-recording, and issues a new av-certificate. mimicking a chosen person of whom sufficient audiovisual information has been collected in advance.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

VideoTicket

Nali

Oorschot

Adler

2008

Proceedings of the 2007 Workshop on New Security Paradigms

View full text Add to dashboard Cite

Identity fraud (IDF) may be defined informally as exploitation of credential information using some form of impersonation or misrepresentation of identity, in the context of transactions. Thus, IDF may be viewed as a combination of two old problems: user authentication and transaction authorization. We propose an innovative approach to detect IDF attempts, by combining av-certificates (digitally-signed audiovisual recordings in which users identify themselves) with av-signatures (audiovisual recordings showing users' explicit consent for unique transaction details). Av-certificates may be used in on-site transactions, to confirm user identity. In the case of remote (e.g. web-based) transactions, both av-certificates and av-signatures may be used to authenticate users and verify their consent for transaction details. Conventional impersonation attacks, whereby credentials (e.g. passwords, biometrics, or signing keys) are used without the consent of their legitimate users, fail against VideoTicket. The proposed solution assumes that identity thieves have access to such credentials.Public Key Setup. B generates for itself a signaturerelated public-private key pair (eB, dB), and V obtains an authentic copy of eB. If R = V , R and V may also obtain authentic copies of each other's signature and encryptionrelated public keys to realize authenticated, confidentialityprotected, and integrity-protected communication channels between them. Replay-Protection Setup. V creates a table EV (used inStep 4 of Section 2.3) to detect replay attacks. EV contains

show abstract

Section: Related Workmentioning

confidence: 99%

“…It is assumed that A is not able to forge audiovisual clips in which chosen victims speak chosen transaction details, with chosen voice characteristics, and in such a way that lips and face movements are convincingly synchronized with speech 13. VideoTicket does not rely on end-users' digital signatures.…”

mentioning

confidence: 99%

VideoTicket

Nali

Oorschot

Adler

2008

Proceedings of the 2007 Workshop on New Security Paradigms

View full text Add to dashboard Cite

show abstract

“…Hence, an increased interest occurred in the development of text-toaudiovisual speech synthesis (TTAVS) which consists in augmenting classical TTS systems with a visual component representing a talking face [7].…”

Section: Introductionmentioning

confidence: 99%

Appearance based lip tracking and cloning on speaking faces

Abboud

Chollet

2005

ISPA 2005. Proceedings of the 4th International Symposium on Image and Signal Processing and Analysis, 2005.

View full text Add to dashboard Cite

This paper addresses the issue of lip tracking and cloning using appearance models. In this perspective, a statistical color-based lip detector is first used to classify the pixels of an image into lip and non-lip pixels. This rough estimation of the lip position is then used to initialize an appearance model. This models convergence allows to refine the positions of the MPEG-4 compatible feature points placed around the lip contours. The optimal position of the feature points is then used as a first estimate to compute the position at the next frame of an image sequence to perform speaking lip tracking. To animate an unknown face image in such a way that it reproduces the lip motion of the driving sequence a piecewise affine transform is applied forcing the target lips feature points to match the automatically detected feature points of each frame of the training sequence to perform lip motion cloning. Preliminary results show that the synthetic talking faces obtained are photorealistic and reproduce accurately the movements of the tracked mouth.

show abstract