Related papers: Chameleon: A Hybrid Secure Computation Framework f…
Fully homomorphic encryption (FHE) enables direct computation on encrypted data, making it a crucial technology for privacy protection. However, FHE suffers from significant performance bottlenecks. In this context, GPU acceleration offers…
Secure function evaluation (SFE) is the process of computing a function (or running an algorithm) on some data, while keeping the input, output and intermediate results hidden from the environment in which the function is evaluated. This…
Homomorphic encryption (HE) is widely adopted in untrusted environments such as federated learning. A notable limitation of conventional single-key HE schemes is the stringent security assumption regarding collusion between the parameter…
A protocol for two-party secure function evaluation (2P-SFE) aims to allow the parties to learn the output of function $f$ of their private inputs, while leaking nothing more. In a sense, such a protocol realizes a trusted oracle that…
On-device learning at the edge enables low-latency, private personalization with improved long-term robustness and reduced maintenance costs. Yet, achieving scalable, low-power end-to-end on-chip learning, especially from real-world…
We present SEALion: an extensible framework for privacy-preserving machine learning with homomorphic encryption. It allows one to learn deep neural networks that can be seamlessly utilized for prediction on encrypted data. The framework…
Developing, scaling, and deploying modern Machine Learning solutions remains challenging for small- and middle-sized enterprises (SMEs). This is due to a high entry barrier of building and maintaining a dedicated IT team as well as the…
In this paper, we address the problem of privacy-preserving federated neural network training with $N$ users. We present Hercules, an efficient and high-precision training framework that can tolerate collusion of up to $N-1$ users. Hercules…
The widespread adoption of Machine Learning as a Service raises critical privacy and security concerns, particularly about data confidentiality and trust in both cloud providers and the machine learning models. Homomorphic Encryption (HE)…
The growing popularity of cloud-based machine learning raises a natural question about the privacy guarantees that can be provided in such a setting. Our work tackles this problem in the context where a client wishes to classify private…
We introduce a deep learning framework able to deal with strong privacy constraints. Based on collaborative learning, differential privacy and homomorphic encryption, the proposed approach advances state-of-the-art of private deep learning…
Interactive data visualization and exploration (DVE) applications are often network-bottlenecked due to bursty request patterns, large response sizes, and heterogeneous deployments over a range of networks and devices. This makes it…
Achieving faster execution with shorter compilation time can foster further diversity and innovation in neural networks. However, the current paradigm of executing neural networks either relies on hand-optimized libraries, traditional…
We propose Falcon, an end-to-end 3-party protocol for efficient private training and inference of large machine learning models. Falcon presents four main advantages - (i) It is highly expressive with support for high capacity networks such…
The widespread deployment of products powered by machine learning models is raising concerns around data privacy and information security worldwide. To address this issue, Federated Learning was first proposed as a privacy-preserving…
In contemporary cloud-based services, protecting users' sensitive data and ensuring the confidentiality of the server's model are critical. Fully homomorphic encryption (FHE) enables inference directly on encrypted inputs, but its…
Secure aggregation is commonly used in federated learning (FL) to alleviate privacy concerns related to the central aggregator seeing all parameter updates in the clear. Unfortunately, most existing secure aggregation schemes ignore two…
Adversarial misuse, particularly through `jailbreaking' that circumvents a model's safety and ethical protocols, poses a significant challenge for Large Language Models (LLMs). This paper delves into the mechanisms behind such successful…
Federated learning is a method used in machine learning to allow multiple devices to work together on a model without sharing their private data. Each participant keeps their private data on their system and trains a local model and only…
We present Chameleon, a family of early-fusion token-based mixed-modal models capable of understanding and generating images and text in any arbitrary sequence. We outline a stable training approach from inception, an alignment recipe, and…