A Stealthy Wrongdoer: Feature-Oriented Reconstruction Attack against Split Learning

arXiv:2405.04115v1 Announce Type: new
Abstract: Split Learning (SL) is a distributed learning framework renowned for its privacy-preserving features and minimal computational requirements. Previous research consistently highlights the potential privacy breaches in SL systems by server adversaries reconstructing training data. However, these studies often rely on strong assumptions or compromise system utility to enhance attack performance. This paper introduces a new semi-honest Data Reconstruction Attack on SL, named Feature-Oriented Reconstruction Attack (FORA). In contrast to prior works, FORA relies on limited …

adversaries arxiv attack breaches compromise computational cs.cr data distributed feature features framework privacy requirements research server split learning studies system systems training training data utility