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 …
SoK: cryptographic neural-network computation
We studied 53 privacy-preserving neural-network papers in 2016-2022 based on
cryptography (without trusted processors or differential privacy), 16 of which only use …
cryptography (without trusted processors or differential privacy), 16 of which only use …
Orca: FSS-based Secure Training and Inference with GPUs
Secure Two-party Computation (2PC) allows two parties to compute any function on their
private inputs without revealing their inputs to each other. In the offline/on-line model for …
private inputs without revealing their inputs to each other. In the offline/on-line model for …
A survey of trustworthy federated learning with perspectives on security, robustness and privacy
Trustworthy artificial intelligence (AI) technology has revolutionized daily life and greatly
benefited human society. Among various AI technologies, Federated Learning (FL) stands …
benefited human society. Among various AI technologies, Federated Learning (FL) stands …
Ciphergpt: Secure two-party gpt inference
ChatGPT is recognized as a significant revolution in the field of artificial intelligence, but it
raises serious concerns regarding user privacy, as the data submitted by users may contain …
raises serious concerns regarding user privacy, as the data submitted by users may contain …
" Get in Researchers; We're Measuring Reproducibility": A Reproducibility Study of Machine Learning Papers in Tier 1 Security Conferences
D Olszewski, A Lu, C Stillman, K Warren… - Proceedings of the …, 2023 - dl.acm.org
Reproducibility is crucial to the advancement of science; it strengthens confidence in
seemingly contradictory results and expands the boundaries of known discoveries …
seemingly contradictory results and expands the boundaries of known discoveries …
Sigma: Secure gpt inference with function secret sharing
K Gupta, N Jawalkar, A Mukherjee… - Cryptology ePrint …, 2023 - eprint.iacr.org
Abstract Secure 2-party computation (2PC) enables secure inference that offers protection
for both proprietary machine learning (ML) models and sensitive inputs to them. However …
for both proprietary machine learning (ML) models and sensitive inputs to them. However …
Pika: Secure computation using function secret sharing over rings
S Wagh - Proceedings on Privacy Enhancing Technologies, 2022 - petsymposium.org
Machine learning algorithms crucially depend on non-linear mathematical functions such as
division (for normalization), exponentiation (for softmax and sigmoid), tanh (as an activation …
division (for normalization), exponentiation (for softmax and sigmoid), tanh (as an activation …
Honeycomb: Secure and Efficient {GPU} Executions via Static Validation
Graphics Processing Units (GPUs) unlock emerging use cases like large language models
and autonomous driving. They process a large amount of sensitive data, where security is of …
and autonomous driving. They process a large amount of sensitive data, where security is of …
He3db: An efficient and elastic encrypted database via arithmetic-and-logic fully homomorphic encryption
As concerns are increasingly raised about data privacy, encrypted database management
system (DBMS) based on fully homomorphic encryption (FHE) attracts increasing research …
system (DBMS) based on fully homomorphic encryption (FHE) attracts increasing research …