Towards practical secure neural network inference: the journey so far and the road ahead
Neural networks (NNs) have become one of the most important tools for artificial
intelligence. Well-designed and trained NNs can perform inference (eg, make decisions or …
intelligence. Well-designed and trained NNs can perform inference (eg, make decisions or …
SafeFL: MPC-friendly framework for private and robust federated learning
Federated learning (FL) has gained widespread popularity in a variety of industries due to its
ability to locally train models on devices while preserving privacy. However, FL systems are …
ability to locally train models on devices while preserving privacy. However, FL systems are …
FLUTE: fast and secure lookup table evaluations
The concept of using Lookup Tables (LUTs) instead of Boolean circuits is well-known and
been widely applied in a variety of applications, including FPGAs, image processing, and …
been widely applied in a variety of applications, including FPGAs, image processing, and …
Sequre: a high-performance framework for secure multiparty computation enables biomedical data sharing
Secure multiparty computation (MPC) is a cryptographic tool that allows computation on top
of sensitive biomedical data without revealing private information to the involved entities …
of sensitive biomedical data without revealing private information to the involved entities …
Vasa: Vector aes instructions for security applications
Due to standardization, AES is today's most widely used block cipher. Its security is well-
studied and hardware acceleration is available on a variety of platforms. Following the …
studied and hardware acceleration is available on a variety of platforms. Following the …
SynCirc: efficient synthesis of depth-optimized circuits for secure computation
Secure Multi-party Computation (MPC) allows to securely compute on private data. To make
MPC practical, logic synthesis can be used to automatically translate a description of the …
MPC practical, logic synthesis can be used to automatically translate a description of the …
Studying the challenges of develo** hardware description language programs
Context: Develo** domain specific architectures (eg, Google's TPU) typically requires
writing programs in Hardware Description Languages (HDLs). Compared to traditional …
writing programs in Hardware Description Languages (HDLs). Compared to traditional …
Combine: compilation and backend-independent vectorization for multi-party computation
B Levy, M Ishaq, B Sherman, L Kennard… - Proceedings of the …, 2023 - dl.acm.org
Recent years have witnessed significant advances in programming technology for multi-
party computation (MPC), bringing MPC closer to practice and wider applicability. Typical …
party computation (MPC), bringing MPC closer to practice and wider applicability. Typical …
Fuse–flexible file format and intermediate representation for secure multi-party computation
Secure Multi-Party Computation (MPC) is continuously becoming more and more practical.
Many optimizations have been introduced, making MPC protocols more suitable for solving …
Many optimizations have been introduced, making MPC protocols more suitable for solving …
FLUTE: Fast and Secure Lookup Table Evaluations (Full Version)
The concept of using Lookup Tables (LUTs) instead of Boolean circuits is well-known and
been widely applied in a variety of applications, including FPGAs, image processing, and …
been widely applied in a variety of applications, including FPGAs, image processing, and …