Secure Face De-Identification Framework IntegratingStyleGAN LatentManipulation With FPE

Weproposedareversiblefacialde-identificationframework that integrates symmetric-key format-preserving encryption (FPE)intodeepneuralnetwork-basedface-swappingmodels. Thisworkwasmotivatedbythe increasingneedto securely manage facial data in digital systems while enabling lawful restoration when required. The method supports identity removal and recovery without compromising data structure or visual fidelity. Theproposedframeworkisappliedtotwostruc- turally different de-identification networks—FaceShifter and SimSwap—demonstrating its versatility and modularity. Notably,theapproachmaintainsnon-identityattributessuch as pose and expression while ensuring that the identity informationcanbereconstructedwhenauthorized.Through extensive qualitative and quantitative evaluations, we show that the framework enables high-fidelity face manipulation with minimal perceptual distortion, achieving a favorable trade-off between privacy and utility. Beyonditstechnicalimplementation,thisworkhighlights that reversible de-identification can be securely realized withoutrelyingonvulnerablepassword-basedschemes.Italsocontributestothebroaderunderstandingofhowdiffer- entnetworkarchitecturesaffectde-identificationrobustness under complex visual conditions. The ability to flexibly embed FPE into different models suggests that the method can be extended to other identity-sensitive domains as well. Future research will aim to improve restoration fidelity underhighlyunconstrainedscenariosandexpandapplicabil- ity to additional real-world datasets and edge deployments where privacy guarantees are essential.

[1]     A. Miotti and A. Wasil, ‘‘Combatting deepfakes: Policies to addressnational security threats and rights violations,’’ 2024, arXiv:2402.09581. [2]     European Commission. (2018). Eu Data Protection Rules. Accessed:Sep.12,2024.[Online].Available:https://commission.europa.eu/law/law-topic/data-protection/data-protection-euen [3]     J. Song, J. Kim, and J. Nang, ‘‘Face de-identification using convolutionalneuralnetwork(CNN)modelsforvisual-copydetection,’’Appl.Sci.,vol. 14, no. 5, p. 1771, Feb. 2024. [4]     Y. Wen, B. Liu, L. Song, J. Cao, and R. Xie, ‘‘Differential privateidentification protection for face images,’’ in Face De-Identification:Safeguarding Identities in the Digital Era. Cham, Switzerland: Springer,2024, pp. 75–108. [5]     J. Cao, B. Liu, Y. Wen, R. Xie, and L. Song, ‘‘Personalized andinvertible face de-identification by disentangled identity informationmanipulation,’’inProc.IEEE/CVFInt.Conf.Comput.Vis.(ICCV),Oct. 2021, pp. 3314–3322. [6]     D. Li, W. Wang, K. Zhao, J. Dong, and T. Tan, ‘‘RiDDLE: Reversibleand diversified de-identification with latent encryptor,’’ 2023,arXiv:2303.05171. [7]     D.Xiao,J.Xia,M.Li,andM.Zhang,‘‘Manipulable,reversibleand diversified de-identification via face identity disentanglement,’’Multimedia Tools Appl., vol. 83, no. 31, pp. 75653–75670, Feb. 2024. [8]     Y.Wen,B.Liu,L.Song,J.Cao,andR.Xie,‘‘Deepmotionflowguidedreversiblefacevideode-identification,’’inFaceDe-identification:Safeguarding Identities in the Digital Era. Cham, Switzerland: Springer,2024, pp. 147–176. [9]     M.Bellare,T.Ristenpart,P.Rogaway,andT.Stegers,‘‘Format-preservingencryption,’’inProc.Sel.AreasCryptography:16thAnnu.Int.Workshop.Alberta, ED, Canada: Springer, Jan. 2009, pp. 295–312. [10]     L.Li, J.Bao, H. Yang, D.Chen, and F.Wen,‘‘FaceShifter:Towards highfidelity and occlusion aware face swapping,’’ 2019, arXiv:1912.13457.