arXiv Machine Learning

LightSplit: Practical Privacy-Preserving Split Learning via Orthogonal Projections (Full Version)

LightSplit introduces a lightweight orthogonal random projection at the split learning cut layer to reduce communication overhead and limit information exposure. By sending low‑dimensional projections instead of raw activations, the method preserves end‑to‑end differentiability while discarding irreversibly part of the representation, thereby mitigating reconstruction attacks. Experiments on seven benchmarks show up to 32× compression with minimal accuracy loss and strong resistance to state‑of‑the‑art inversion attacks.

arXiv AI

5d ago

FedSumUp: User-Auditable Privacy-Aware Representation Sharing for Resource-Constrained Federated Intelligence

FedSumUp introduces a learnable lossy compressor that generates compact, visually interpretable representations on client devices, reducing privacy leakage and computational overhead. The compressor is trained on the server using a data‑free closed‑loop optimization that minimizes the difference between original and twice‑compressed representations after upsampling. Experiments on BloodMNIST, CIFAR‑10, and ChestMNIST show low reconstruction PSNR, significant client runtime reductions, and competitive classification accuracy while remaining robust to non‑IID data.

By Jingwei Zhao, Tiantong Sun, Yuanyuan Song, Jinhuan Guo, Wei Zishuo, Shengyu Huang, Ziyuan Ren, Wei Chen, Xiaojin Zhang

safety

arXiv Machine Learning

Aug 18

A Privacy Study of Sparse Collaborative Inference

arXiv:2608. 16236v1 Announce Type: new Abstract: Collaborative inference (CI) splits a model between an edge device and a server, whereby the client computes an intermediate activation, transmits it, and the server completes the computation.

By Maximilian Andreas Hoefler, Karsten Mueller, Wojciech Samek

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 Machine Learning

Jul 31

TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement

arXiv:2607. 27940v1 Announce Type: new Abstract: Federated fine-tuning of large language models (LLMs) enables collaborative training without exposing raw data.

By Cheng Wei (Honor Device Co., Ltd., Shenzhen, China)

llms fine-tuning safety

Hugging Face Trending Papers

Jul 30

TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement

Federated fine-tuning of large language models (LLMs) enables collaborative training without exposing raw data. However, a recent attack, NeuroImprint [1] (arXiv:2606.

llms fine-tuning safety

arXiv Machine Learning

Jun 2

Profiling Privacy Preservation Against Gradient Inversion Attacks in Tabular Federated Learning

arXiv:2606. 00986v1 Announce Type: new Abstract: Federated learning (FL) enables multiple data holders to train machine learning models collaboratively without centralizing raw data, making it useful in privacy sensitive domains such as healthcare and institutional data sharing.

By Ivo Osterberg Nilsson, Maximilian Birr Engvall, Viktor Valadi, Teddy Lazebnik

llms 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

arXiv Computer Vision

Sep 30

From Laboratory to Real World: A New Benchmark Towards Privacy-Preserved Visible-Infrared Person Re-Identification

arXiv:2503.12232v3 Announce Type: replace Abstract: Aiming to match pedestrian images captured under varying lighting conditions, visible-infrared person re-identification (VI-ReID) has drawn intensi...

By Yan Jiang, Hao Yu, Xu Cheng, Haoyu Chen, Zhaodong Sun, Guoying Zhao

benchmarks safety

arXiv Machine Learning

Jun 25

TL++: Accuracy and Privacy Preserving Traversal Learning for Distributed Intelligent Systems

arXiv:2606. 25627v1 Announce Type: new Abstract: Distributed intelligent systems increasingly need to train across data silos without centralizing raw data.

By Erdenebileg Batbaatar, Young Yoon

fine-tuning safety

arXiv Machine Learning

Jun 16

FEnc$^2$: Unifying Data Packing for Efficient Private Inference via Convolution and Architecture-Aware Fragment Encoding

arXiv:2606. 16359v1 Announce Type: cross Abstract: Fully Homomorphic Encryption (FHE) enables privacy-preserving machine learning but incurs extreme computational and memory overhead.

By Ran Ran, Zhaoting Gong, Nuo Xu, Yuanchao Xu, Fan Yao, Wujie Wen

benchmarks safety

arXiv AI

Oct 7

SpliTEE: Fast and Private LLM Inference by Coupling GPU-Assisted Trusted Execution Environments with Differential Privacy

arXiv:2609.15039v3 Announce Type: replace-cross Abstract: User prompts provided to large language models (LLMs) may contain private information. One way to protect them is to execute the LLM inside a...

By Shashie Dilhara Batan Arachchige, Robin Carpentier, Hassan Jameel Asghar, Dali Kaafar

llms efficiency safety

arXiv Machine Learning

Sep 2

Contribution-Aware Bandwidth Allocation for Multimodal Split Learning

The paper introduces ModalShare, a bandwidth allocation method for multimodal split learning that assigns each modality a keep‑ratio based on its Shapley contribution score. Unlike existing compression schemes that split the uplink budget proportionally to activation size, ModalShare explicitly optimizes the split across modalities, requiring no extra uplink traffic or client computation. Experiments on CREMA‑D and MVSA datasets show that ModalShare improves accuracy by 12.4–15.4 percentage points over equal keep‑ratios under a 5× compression budget, outperforming three compressors across multiple datasets and budgets.

By Iason Ofeidis, Leandros Tassiulas

multimodal

Related stories