@inproceedings{BayerlBrasserBuschetal.2019, author = {Bayerl, Sebastian P. and Brasser, Ferdinand and Busch, Christoph and Frassetto, Tommaso and Jauernig, Patrick and Kolberg, Jascha and Nautsch, Andreas and Riedhammer, Korbinian and Sadeghi, Ahmad-Reza and Schneider, Thomas and Stapf, Emmanuel and Treiber, Amos and Weinert, Christian}, title = {Privacy-preserving speech processing via STPC and TEEs (Poster)}, year = {2019}, language = {en} } @inproceedings{BayerlFrasettoJauernigetal.2020, author = {Bayerl, Sebastian P. and Frasetto, Tommaso and Jauernig, Patrick and Riedhammer, Korbinian and Sadeghi, Ahmad-Reza and Schneider, Thomas and Stapf, Emmanuel and Weinert, Christian}, title = {Offline Model Guard}, doi = {10.48550/arXiv.2007.02351}, pages = {6}, year = {2020}, abstract = {Performing machine learning tasks in mobile applications yields a challenging conflict of interest: highly sensitive client information (e.g., speech data) should remain private while also the intellectual property of service providers (e.g., model parameters) must be protected. Cryptographic techniques offer secure solutions for this, but have an unacceptable overhead and moreover require frequent network interaction. In this work, we design a practically efficient hardware-based solution. Specifically, we build Offline Model Guard (OMG) to enable privacy-preserving machine learning on the predominant mobile computing platform ARM - even in offline scenarios. By leveraging a trusted execution environment for strict hardware-enforced isolation from other system components, OMG guarantees privacy of client data, secrecy of provided models, and integrity of processing algorithms. Our prototype implementation on an ARM HiKey 960 development board performs privacy-preserving keyword recognition using TensorFlow Lite for Microcontrollers in real time.}, language = {en} } @inproceedings{BayerlFrassettoJauernigetal.2020, author = {Bayerl, Sebastian P. and Frassetto, Tommaso and Jauernig, Patrick and Riedhammer, Korbinian and Sadeghi, Ahmad-Reza and Schneider, Thomas and Stapf, Emmanuel and Weinert, Christian}, title = {Offline Model Guard: Secure and Private ML on Mobile Devices}, series = {2020 Design, Automation \& Test in Europe Conference \& Exhibition (DATE)}, booktitle = {2020 Design, Automation \& Test in Europe Conference \& Exhibition (DATE)}, publisher = {IEEE}, doi = {10.23919/DATE48585.2020.9116560}, pages = {6}, year = {2020}, abstract = {Performing machine learning tasks in mobile applications yields a challenging conflict of interest: highly sensitive client information (e.g., speech data) should remain private while also the intellectual property of service providers (e.g., model parameters) must be protected. Cryptographic techniques offer secure solutions for this, but have an unacceptable overhead and moreover require frequent network interaction.In this work, we design a practically efficient hardware-based solution. Specifically, we build OFFLINE MODEL GUARD (OMG) to enable privacy-preserving machine learning on the predominant mobile computing platform ARM—even in offline scenarios. By leveraging a trusted execution environment for strict hardware-enforced isolation from other system components, OMG guarantees privacy of client data, secrecy of provided models, and integrity of processing algorithms. Our prototype implementation on an ARM HiKey 960 development board performs privacy-preserving keyword recognition using TensorFlow Lite for Microcontrollers in real time.}, language = {en} }