Gradient Inversion Exposes Privacy Leakage in Federated LoRA-Tuned Vision Transformers
This paper studies private-data leakage in federated learning when Vision Transformers are fine-tuned with LoRA, where low-rank updates weaken the gradient signal available to the server. It proposes a spatially anchored generative inversion framework that introduces server-prescribed trainable positional embeddings during client fine-tuning, using the resulting positional gradients as layer-wise spatial anchors. The method reports PSNR gains of 10.14 dB, SSIM gain of 0.45 and LPIPS gain of 0.098 on CIFAR-10, plus PSNR gains of 7.83 dB and 11.74 dB on CelebA and CARS in the FedSGD setting. The authors conclude that LoRA-based parameter-efficient fine-tuning does not by itself prevent data leakage in federated learning.
It gives privacy and federated-learning practitioners concrete evidence that LoRA does not automatically protect client data and describes an attack that improves reconstruction quality.
Comments & Questions (0)
No comments yet
Be the first to comment!