Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Mühl, Christopher"'
When training a machine learning model with differential privacy, one sets a privacy budget. This budget represents a maximal privacy violation that any user is willing to face by contributing their data to the training set. We argue that this approa
Externí odkaz:
http://arxiv.org/abs/2303.17046
Applying machine learning (ML) to sensitive domains requires privacy protection of the underlying training data through formal privacy frameworks, such as differential privacy (DP). Yet, usually, the privacy of the training data comes at the cost of
Externí odkaz:
http://arxiv.org/abs/2202.10517
Publikováno v:
Proceedings on Privacy Enhancing Technologies. 2023:158-176
Applying machine learning (ML) to sensitive domains requires privacy protection of the underlying training data through formal privacy frameworks, such as differential privacy (DP). Yet, usually, the privacy of the training data comes at the cost of
Autor:
Wisiol, Nils, Mühl, Christopher, Pirnay, Niklas, Nguyen, Phuong Ha, Margraf, Marian, Seifert, Jean-Pierre, Dijk, Marten, Rührmair, Ulrich
Publikováno v:
Transactions on Cryptographic Hardware and Embedded Systems, Vol 2020, Iss 3 (2020)
IACR Transactions on Cryptographic Hardware and Embedded Systems, 2020(3), 97-120
IACR Transactions on Cryptographic Hardware and Embedded Systems, 2020(3), 97-120
We demonstrate that the Interpose PUF proposed at CHES 2019, an Arbiter PUF-based design for so-called Strong Physical Unclonable Functions (PUFs), can be modeled by novel machine learning strategies up to very substantial sizes and complexities. Our