English(EN) Breaking the Privacy Promise: Gradient Inversion Attacks on Federated Low-Rank Adapted Vision Transformers

新框架揭示了联邦 LoRA 适配视觉 Transformer 中的隐私风险

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-09 05:00

研究人员开发了一个新框架，用于解决在使用 LoRA 等参数高效微调方法和视觉 Transformer 进行联邦学习时出现的隐私风险。所提出的空间锚定生成反演框架通过将可训练的位置嵌入整合到 ViT 块中，提高了私有数据的重建质量。该方法在 CIFAR-10、CelebA 和 CARS 等数据集上显著提高了 PSNR、SSIM 和 LPIPS 等图像重建指标，表明仅基于 LoRA 的微调本身并不能固有地防止联邦学习中的数据泄露。 AI

影响强调了在使用高效微调技术进行视觉模型联邦学习设置中潜在的隐私漏洞。

排序理由研究论文，详细介绍了一种针对联邦学习模型的新梯度反演攻击方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 15 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 研究论文，详细介绍了一种针对联邦学习模型的新梯度反演攻击方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Ritik K. Badiya, Siladittya Manna, Ashmit Sinha, M Yashwanth, Anirban Chakraborty · 2026-11-09 05:00

打破隐私承诺：针对联邦低秩适配视觉Transformer的梯度反演攻击

arXiv:2611.09652v1 Announce Type: new Abstract: 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 communica…

本文如何被排名

报道来源 [1]

打破隐私承诺：针对联邦低秩适配视觉Transformer的梯度反演攻击

相关实体

相关话题