Year: 2022
Type: article
Abstract: State-of-the-art template reconstruction attacks assume that an adversary has access to a part or whole of the functionality of a target model.However, in a practical scenario, rigid protection of the target system prevents them from gaining knowledge of the target model.In this paper, we propose a novel template reconstruction attack method utilizing a feature converter.The feature converter enables an adversary to reconstruct an image from a corresponding compromised template without knowledge about the target model.The proposed method was evaluated with qualitative and quantitative measures.We achieved the Successful Attack Rate(SAR) of 0.90 on Labeled Faces in the Wild Dataset(LFW) with compromised templates of only 1280 identities.
Authors: Gesellschaft für Informatik 2022 Darmstadt, Brömme, Arslan, Damer, Naser 1985-, Gomez Barrero, Marta 1988-, Raja, Kiran, Rathgeb, Christian 1984-, Sequeira, Ana F., Todisco, Massimiliano, Uhl, Andreas 1968-, Gesellschaft für Informatik
Language: German
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: A quantum approach for biometric authentication: micro biometric authentication technology to break into a new physical aspect of biometric information., Secure Computing Platform in the AI Era, Surveillance Camera Image Analysis for Person Understanding: Development of Recognition and Authentication Technology for Walking, Running, and Cycling Individuals, I/UCRC Phase II: Center for Identification Technology Research, Development of a fair and secure online testing system using biometrics and artificial intelligence technology
OpenAlex ID: W7026967670