2022 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS) 2022
DOI: 10.1109/ispass55109.2022.00025
|View full text |Cite
|
Sign up to set email alerts
|

Characterization of MPC-based Private Inference for Transformer-based Models

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
3
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
2

Relationship

2
4

Authors

Journals

citations
Cited by 6 publications
(3 citation statements)
references
References 8 publications
0
3
0
Order By: Relevance
“…Nevertheless, according to our experiences with machine learning inference, for plaintext insecure inferences using single-precision floating points, inputs to exponential functions are small so that the x max can be omitted. However, according to a recent study for MPC Transformer-based models [34], due to MPC numerical limitations and linear approximations, using the x max is vital to model performance accuracy. Omitting or replacing the x max to stabilize exponential functions can destroy model accuracy.…”
Section: F Numerical Instability In the Softmaxmentioning
confidence: 99%
See 1 more Smart Citation
“…Nevertheless, according to our experiences with machine learning inference, for plaintext insecure inferences using single-precision floating points, inputs to exponential functions are small so that the x max can be omitted. However, according to a recent study for MPC Transformer-based models [34], due to MPC numerical limitations and linear approximations, using the x max is vital to model performance accuracy. Omitting or replacing the x max to stabilize exponential functions can destroy model accuracy.…”
Section: F Numerical Instability In the Softmaxmentioning
confidence: 99%
“…Sphynx [3], DeepReduce [14], and Circa [9] has proposed optimizations to optimize MPC CNNs. [34] is an extensive study on MPC inference of Transformer-based models and urges for optimizations for MPC Softmax.…”
Section: B Mpc Operation Optimizationsmentioning
confidence: 99%
“…There are various algorithmic approaches to protect data privacy, such as Homomorphic Encryption libraries [23,25,39,45], Secure Multi-Party Computing (MPC) [53,54,70,74,79,81], Differential Privacy [1,19,75], Noise Injection [20,47,48], and using Trusted Execution Enviroments [57,77]. Each of these methods provides a different privacy guarantee and comes at different cost [49], as we explain in the next section.…”
mentioning
confidence: 99%