Hugging Face Trending Papers July 27, 2026

BettiSplit: Topology-Guided Privacy-Aware Split Learning Against Feature Inversion and Gradient Leakage

Read the original on Hugging Face Trending Papers →

Split learning enables collaborative model training by partitioning neural networks across clients and servers. However, improper split placement can lead to severe privacy leakage through intermediate representations.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

safety

arXiv AI

Jul 28

BettiSplit: Topology-Guided Privacy-Aware Split Learning Against Feature Inversion and Gradient Leakage

arXiv:2607. 24556v1 Announce Type: cross Abstract: Split learning enables collaborative model training by partitioning neural networks across clients and servers.

By Akarsh K. Nair, Muhammad Arifur Rahman, David Brown, Mufti Mahmud

safety

arXiv AI

2d ago

CutClean: Neural Network Pruning for Privacy-Preserving Inference

arXiv:2608. 13773v1 Announce Type: cross Abstract: Neural networks are increasingly deployed in high-stakes applications with growing privacy leakage concerns.

By Leonardo Magliolo, Vito Paolo Pastore, Giuseppe Valenzise, Enzo Tartaglione

efficiency safety

arXiv Machine Learning

Jul 7

GDBR: Label Recovery Attack Against Partial Gradient Encryption in Federated Learning

arXiv:2412. 12640v2 Announce Type: replace Abstract: The increasing demand for data privacy, alongside the benefits of aggregating data from networked devices, has catalyzed the emergence of federated learning (FL).

By Rui Zhang, Ka-Ho Chow

llms safety

arXiv AI

Aug 5

PRIVEE: Privacy-Preserving Vertical Federated Learning Against Feature Inference Attacks

arXiv:2512. 12840v2 Announce Type: replace-cross Abstract: Vertical Federated Learning (VFL) enables collaborative model training across organizations that share common user samples but hold disjoint feature spaces.

By Sindhuja Madabushi, Haider Ali, Ahmad Faraz Khan, Rui Ning, Hongyi Wu, Chunsheng Xin, Ali. R. Butt, Jin-Hee Cho

safety

arXiv AI

Jun 15

From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models

arXiv:2606. 14210v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in privacy-sensitive domains, where users must balance the risk of data exposure through external APIs against the high computational cost of local deployment.

By Zixuan Gu, Xiaojun Ye, Yang Liu

llms fine-tuning benchmarks safety

arXiv Machine Learning

Jun 2

Random Erasing vs. Model Inversion: A Promising Defense or a False Hope?

arXiv:2409. 01062v4 Announce Type: replace Abstract: Model Inversion (MI) attacks pose a significant privacy threat by reconstructing private training data from machine learning models.

By Viet-Hung Tran, Ngoc-Bao Nguyen, Son T. Mai, Hans Vandierendonck, Ira Assent, Alex Kot, Ngai-Man Cheung

benchmarks safety

Related stories

BettiSplit: Topology-Guided Privacy-Aware Split Learning Against Feature Inversion and Gradient Leakage

CutClean: Neural Network Pruning for Privacy-Preserving Inference

GDBR: Label Recovery Attack Against Partial Gradient Encryption in Federated Learning

PRIVEE: Privacy-Preserving Vertical Federated Learning Against Feature Inference Attacks

From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models

Random Erasing vs. Model Inversion: A Promising Defense or a False Hope?