Garbled Neural Networks are Practical

By Marshall Ball, Brent Carmer, Tal Malkin, Mike Rosulek, Nichole Schimanski. 2019

52 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Marcel Keller
2. Assi Barak
3. Daniel E. Escudero
4. Bo Li
5. Anders Dalskov
6. Peng Qi
7. Bowen Zhou
8. Jinfeng Yi

Citations in the corpus

• Secure Evaluation of Quantized Neural Networks (2019, methodology): “s [34] (i.e., networks with weights that are bits) can be evaluated very efficiently. XONN shows that evaluating deep networks (>20 layers) is possible. A different approach is taken by Ball et al. [2] where the authors use the arithmetic garbling technique of Ball et al. [3] to evaluate Neural Ne”
• Trustworthy AI: From Principles to Practices (2021, methodology): “To reduce the high costs of computation and communication of the SMPC, parameter quantization and function approximation were used together with cryptographic protocols in References [8, 32].”
• Survey of Attacks and Defenses on Edge-Deployed Neural Networks (2019, background): “In [77], authors present a modified GC that supports free addition and constant-multiplication on a limited integer range, and a significantly cheaper activation function.”