Advances and open problems in federated learning
Federated learning (FL) is a machine learning setting where many clients (eg, mobile
devices or whole organizations) collaboratively train a model under the orchestration of a …
devices or whole organizations) collaboratively train a model under the orchestration of a …
Federated learning vulnerabilities, threats and defenses: A systematic review and future directions
S Almutairi, A Barnawi - Internet of Things, 2023 - Elsevier
Today, a broad range of items, ranging from smartphones to smart cars are connected
together via the Internet, also known as the Internet of Things (IoT). The IoT is powered by …
together via the Internet, also known as the Internet of Things (IoT). The IoT is powered by …
Posthoc privacy guarantees for collaborative inference with modified Propose-Test-Release
Cloud-based machine learning inference is an emerging paradigm where users query by
sending their data through a service provider who runs an ML model on that data and …
sending their data through a service provider who runs an ML model on that data and …
Adasplit: Adaptive trade-offs for resource-constrained distributed deep learning
Distributed deep learning frameworks like federated learning (FL) and its variants are
enabling personalized experiences across a wide range of web clients and mobile/IoT …
enabling personalized experiences across a wide range of web clients and mobile/IoT …
Split HE: Fast secure inference combining split learning and homomorphic encryption
GL Pereteanu, A Alansary… - arXiv preprint arXiv …, 2022 - arxiv.org
This work presents a novel protocol for fast secure inference of neural networks applied to
computer vision applications. It focuses on improving the overall performance of the online …
computer vision applications. It focuses on improving the overall performance of the online …
[HTML][HTML] A comprehensive analysis of model poisoning attacks in federated learning for autonomous vehicles: A benchmark study
S Almutairi, A Barnawi - Results in Engineering, 2024 - Elsevier
Due to the increase in data regulations amid rising privacy concerns, the machine learning
(ML) community has proposed a novel distributed training paradigm called federated …
(ML) community has proposed a novel distributed training paradigm called federated …
A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learning
Split Learning (SL) is a distributed learning framework renowned for its privacy-preserving
features and minimal computational requirements. Previous research consistently highlights …
features and minimal computational requirements. Previous research consistently highlights …
Context-aware hybrid encoding for privacy-preserving computation in IoT devices
Recent years have witnessed a surge in hybrid IoT-cloud applications where an end user
distributes the desired computation between the IoT and cloud nodes. While achieving …
distributes the desired computation between the IoT and cloud nodes. While achieving …
Decouple-and-sample: Protecting sensitive information in task agnostic data release
We propose sanitizer, a framework for secure and task-agnostic data release. While
releasing datasets continues to make a big impact in various applications of computer …
releasing datasets continues to make a big impact in various applications of computer …
GAN you see me? enhanced data reconstruction attacks against split inference
Z Li, M Yang, Y Liu, J Wang, H Hu… - Advances in Neural …, 2024 - proceedings.neurips.cc
Split Inference (SI) is an emerging deep learning paradigm that addresses computational
constraints on edge devices and preserves data privacy through collaborative edge-cloud …
constraints on edge devices and preserves data privacy through collaborative edge-cloud …