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 …
Intel software guard extensions applications: A survey
NC Will, CA Maziero - ACM Computing Surveys, 2023 - dl.acm.org
Data confidentiality is a central concern in modern computer systems and services, as
sensitive data from users and companies are being increasingly delegated to such systems …
sensitive data from users and companies are being increasingly delegated to such systems …
Secure quantized training for deep learning
We implement training of neural networks in secure multi-party computation (MPC) using
quantization commonly used in said setting. We are the first to present an MNIST classifier …
quantization commonly used in said setting. We are the first to present an MNIST classifier …
Mesas: Poisoning defense for federated learning resilient against adaptive attackers
T Krauß, A Dmitrienko - Proceedings of the 2023 ACM SIGSAC …, 2023 - dl.acm.org
Federated Learning (FL) enhances decentralized machine learning by safeguarding data
privacy, reducing communication costs, and improving model performance with diverse data …
privacy, reducing communication costs, and improving model performance with diverse data …
Avocado: A Secure {In-Memory} Distributed Storage System
M Bailleu, D Giantsidi, V Gavrielatos… - 2021 USENIX Annual …, 2021 - usenix.org
We introduce Avocado, a secure in-memory distributed storage system that provides strong
security, fault-tolerance, consistency (linearizability) and performance for untrusted cloud …
security, fault-tolerance, consistency (linearizability) and performance for untrusted cloud …
All Rivers Run to the Sea: Private Learning with Asymmetric Flows
Data privacy is of great concern in cloud machine-learning service platforms when sensitive
data are exposed to service providers. While private computing environments (eg secure …
data are exposed to service providers. While private computing environments (eg secure …
Fairness audit of machine learning models with confidential computing
Algorithmic discrimination is one of the significant concerns in applying machine learning
models to a real-world system. Many researchers have focused on developing fair machine …
models to a real-world system. Many researchers have focused on developing fair machine …
Chex-mix: Combining homomorphic encryption with trusted execution environments for two-party oblivious inference in the cloud
D Natarajan, A Loveless, W Dai… - Cryptology ePrint …, 2021 - eprint.iacr.org
Data, when coupled with state-of-the-art machine learning models, can enable remarkable
applications. But, there exists an underlying tension: users wish to keep their data private …
applications. But, there exists an underlying tension: users wish to keep their data private …
{AI} Psychiatry: Forensic Investigation of Deep Learning Networks in Memory Images
Online learning is widely used in production to refine model parameters after initial
deployment. This opens several vectors for covertly launching attacks against deployed …
deployment. This opens several vectors for covertly launching attacks against deployed …
Citadel: Protecting data privacy and model confidentiality for collaborative learning
Many organizations own data but have limited machine learning expertise (data owners). On
the other hand, organizations that have expertise need data from diverse sources to train …
the other hand, organizations that have expertise need data from diverse sources to train …