Metraipolis › archive › dc_76e536a35978
Breaking the Privacy Promise: Gradient Inversion Attacks on Federated Low-Rank Adapted Vision Transformers — arXiv:2611.09652
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.09652
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-09T22:35:10.213Z
- SHA-256 of the archived text
441aa8db8dcf384e4dba30e127a2c4ea5dbf0c27def51d6116e4ad563780882a- Stable URL of this page
https://metraipolis.com/documento/dc_76e536a35978
How to cite
Breaking the Privacy Promise: Gradient Inversion Attacks on Federated Low-Rank Adapted Vision Transformers — arXiv:2611.09652 — arXiv (en), https://arxiv.org/abs/2611.09652 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_76e536a35978 (Metraipolis archive dc_76e536a35978, sha256 441aa8db8dcf384e4dba30e127a2c4ea5dbf0c27def51d6116e4ad563780882a)
BibTeX
@misc{dc76e536a35978,
title = {Breaking the Privacy Promise: Gradient Inversion Attacks on Federated Low-Rank Adapted Vision Transformers — arXiv:2611.09652},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.09652},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_76e536a35978; sha256 441aa8db8dcf384e4dba30e127a2c4ea5dbf0c27def51d6116e4ad563780882a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09652. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Parameter-efficient fine-tuning (PEFT) has been increasingly adopted to fine-tune pretrained models with low computational cost and is therefore also preferred in the federated learning paradigm to reduce computational and communication overhead. In this work, we investigate the sparsely explored problem of the risk of private data leakage in LoRA-adapted Vision Transformers (ViTs), where low-rank updates weaken the gradient signal available to a server with access to individual client updates. We show that quality of reconstruction is limited by two coupled ambiguities: reduced information in LoRA gradients and missing spatial cues from frozen positional embeddings. To address this, we propose a spatially anchored generative inversion framework that incorporates server-prescribed trainable positional embeddings into ViT blocks during fine-tuning at clients. The resulting positional gradients act as layer-wise spatial anchors, providing additional positional cues, while the generative prior keeps reconstructions on a realistic image manifold, reducing duplicate-data and patch-permutation artifacts, {which produce similar gradients as those produced when the target client images are used}. Adding our proposed spatial anchoring to GIAS improves PSNR by 10.14 dB, SSIM by 0.45, and LPIPS by 0.098 on CIFAR-10, as well as PSNR gains of 7.83 and 11.74 dB on high-resolution CelebA and CARS datasets, respectively, in the FedSGD setting. Such gains in reconstructed image quality metrics are also maintained at higher batch sizes and in FedAvg settings. These results indicate that LoRA-based PEFT does not, by itself, prevent data leakage in FL, and carefully incorporated positional embeddings can help in exposing private information.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.09652 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-09T22:30:47.338Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).