Smart connected farms and networked farmers to improve crop production, sustainability and profitability
To meet the grand challenges of agricultural production including climate change impacts
on crop production, a tight integration of social science, technology and agriculture experts …
on crop production, a tight integration of social science, technology and agriculture experts …
Sok: Privacy-preserving computation techniques for deep learning
J Cabrero-Holgueras, S Pastrana - Proceedings on Privacy …, 2021 - petsymposium.org
Deep Learning (DL) is a powerful solution for complex problems in many disciplines such as
finance, medical research, or social sciences. Due to the high computational cost of DL …
finance, medical research, or social sciences. Due to the high computational cost of DL …
[HTML][HTML] Preserving data privacy in machine learning systems
The wide adoption of Machine Learning to solve a large set of real-life problems came with
the need to collect and process large volumes of data, some of which are considered …
the need to collect and process large volumes of data, some of which are considered …
Coinn: Crypto/ml codesign for oblivious inference via neural networks
We introduce COINN-an efficient, accurate, and scalable framework for oblivious deep
neural network (DNN) inference in the two-party setting. In our system, DNN inference is …
neural network (DNN) inference in the two-party setting. In our system, DNN inference is …
Exploring design and governance challenges in the development of privacy-preserving computation
Homomorphic encryption, secure multi-party computation, and differential privacy are part of
an emerging class of Privacy Enhancing Technologies which share a common promise: to …
an emerging class of Privacy Enhancing Technologies which share a common promise: to …
HELiKs: HE Linear Algebra Kernels for Secure Inference
S Balla, F Koushanfar - Proceedings of the 2023 ACM SIGSAC …, 2023 - dl.acm.org
We introduce HELiKs, a groundbreaking framework for fast and secure matrix multiplication
and 3D convolutions, tailored for privacy-preserving machine learning. Leveraging …
and 3D convolutions, tailored for privacy-preserving machine learning. Leveraging …
Vasa: Vector aes instructions for security applications
JP Münch, T Schneider, H Yalame - Proceedings of the 37th Annual …, 2021 - dl.acm.org
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 …
PG: Byzantine Fault-Tolerant and Privacy-Preserving Sensor Fusion With Guaranteed Output Delivery
We design and implement PG, a Byzantine fault-tolerant and privacy-preserving multi-
sensor fusion system. PG is flexible and extensible, supporting a variety of fusion algorithms …
sensor fusion system. PG is flexible and extensible, supporting a variety of fusion algorithms …
Garbled EDA: Privacy Preserving Electronic Design Automation
The complexity of modern integrated circuits (ICs) necessitates collaboration between
multiple distrusting parties, including third-party intellectual property (3PIP) vendors, design …
multiple distrusting parties, including third-party intellectual property (3PIP) vendors, design …
HWGN: Side-Channel Protected NNs Through Secure and Private Function Evaluation
Recent work has highlighted the risks of intellectual property (IP) piracy of deep learning
(DL) models from the side-channel leakage of DL hardware accelerators. In response …
(DL) models from the side-channel leakage of DL hardware accelerators. In response …