Affine subspace constraints improve federated gradient inversion
The authors report better reconstruction than chosen baselines, including when batch size is moderately overestimated.
Stories per day · 30 days
2 RSS
Relatedfederated-learning2differential-privacy1model-privacy1parameter-efficient-fine-tuning1privacy1vision-transformers1
5 stories, newest first · one card per story
Stories tagged #gradient-inversion
arXiv shows gradient inversion attacks on federated LoRA ViTs
LoRA-adapted Vision Transformers weaken gradient signals allowing private data reconstruction.
What Gradients Add to Text Leakage in Split Language Models, Counted per Token and per Document
Split-learning observers recover 97% of GPT-2 tokens; gradients lift exact document recovery from 14% to 38%.
Temporal Gradient Inversion for Private Trajectory Reconstruction in Embodied Reinforcement Learning
TRACE reconstructs private embodied observation-action trajectories from policy gradients, reaching 18.8 dB PSNR.
Cascading Gradient Inversion via LT-Code Inspired Peeling in Federated Learning
New gradient inversion attacks tied to erasure-coding theory recover 94–100% of ImageNet batches, showing federated learning privacy leakage is underestimated.