{PCAT}: Functionality and data stealing from split learning by {Pseudo-Client} attack
X Gao, L Zhang - 32nd USENIX Security Symposium (USENIX Security …, 2023 - usenix.org
Split learning (SL) is a popular framework to protect a client's training data by splitting up a
model among the client and the server. Previous efforts have shown that a semi-honest …
model among the client and the server. Previous efforts have shown that a semi-honest …
Privacy-Enhancing Technologies for Artificial Intelligence-Enabled Systems
L d'Aliberti, E Gronberg, J Kovba - arXiv preprint arXiv:2404.03509, 2024 - arxiv.org
Artificial intelligence (AI) models introduce privacy vulnerabilities to systems. These
vulnerabilities may impact model owners or system users; they exist during model …
vulnerabilities may impact model owners or system users; they exist during model …
DISTINQT: A Distributed Privacy Aware Learning Framework for QoS Prediction for Future Mobile and Wireless Networks
Beyond 5G and 6G networks are expected to support new and challenging use cases and
applications that depend on a certain level of Quality of Service (QoS) to operate smoothly …
applications that depend on a certain level of Quality of Service (QoS) to operate smoothly …
Investigation on Preserving Privacy of Electronic Medical Record using Split Learning
M Kiruthika, A Kumar, L Krishnasamy… - Procedia Computer …, 2024 - Elsevier
Artificial Intelligence is deployed in multiple areas, including healthcare. Utmost research is
done in AI enabled healthcare industry because of the demands like accurate result, data …
done in AI enabled healthcare industry because of the demands like accurate result, data …
Adaptive Layer Splitting for Wireless LLM Inference in Edge Computing: A Model-Based Reinforcement Learning Approach
Optimizing the deployment of large language models (LLMs) in edge computing
environments is critical for enhancing privacy and computational efficiency. Toward efficient …
environments is critical for enhancing privacy and computational efficiency. Toward efficient …
Functionality and Data Stealing by Pseudo-Client Attack and Target Defenses in Split Learning
L Zhang, X Gao, Y Li, Y Liu - IEEE Transactions on Dependable …, 2024 - ieeexplore.ieee.org
Split learning (SL) aims to protect a client's data by splitting up a neural network among the
client and the server. Previous efforts have shown that a semi-honest server can conduct a …
client and the server. Previous efforts have shown that a semi-honest server can conduct a …
Remaining Time Prediction for Collaborative Business Processes with Privacy Preservation
In collaborative business processes that involve multiple organizations, privacy concerns
prevent organizations from sharing the raw data of their activities. This makes it challenging …
prevent organizations from sharing the raw data of their activities. This makes it challenging …