Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
Gradient inversion attacks aim to reconstruct local training data from intermediate gradients exposed in the federated learning framework. Despite successful attacks, all previous methods, starting from reconstructing a single data point and then relaxing the single-image limit to batch level, are only tested under hard label constraints. Even for single-image reconstruction, we still lack an analysis-based algorithm to recover augmented soft labels. In this work, we change the focus from enlarging batchsize to investigating the hard label constraints, considering a more realistic circumstance where label smoothing and mixup techniques are used in the training process. In particular, we are the first to initiate a novel algorithm to simultaneously recover the ground-truth augmented label and the input feature of the last fully-connected layer from single-input gradients, and provide a necessary condition for any analytical-based label recovery methods. Extensive experiments testify to the label recovery accuracy, as well as the benefits to the following image reconstruction. We believe soft labels in classification tasks are worth further attention in gradient inversion attacks.
Code (1)
Tasks
Federated LearningImage ReconstructionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MGIC: A Multi-Label Gradient Inversion Attack based on Canny Edge Detection on Federated Learning
As a new distributed computing framework that can protect data privacy, federated learning (FL) has attracted more and more attention in recent years. It receives gradients from users to train the global model and releas…
Distributed ComputingEdge DetectionFederated LearningImage ReconstructionJoint Design of RF and gradient waveforms via auto-differentiation for 3D tailored excitation in MRI
This paper proposes a new method for joint design of radiofrequency (RF) and gradient waveforms in Magnetic Resonance Imaging (MRI), and applies it to the design of 3D spatially tailored saturation and inversion pulses. …
Computational EfficiencyAFGI: Towards Accurate and Fast-convergent Gradient Inversion Attack in Federated Learning
Federated learning (FL) empowers privacypreservation in model training by only exposing users' model gradients. Yet, FL users are susceptible to gradient inversion attacks (GIAs) which can reconstruct ground-truth traini…
Edge DetectionFederated LearningMAGIA: Sensing Per-Image Signals from Single-Round Averaged Gradients for Label-Inference-Free Gradient Inversion
We study gradient inversion in the challenging single round averaged gradient SAG regime where per sample cues are entangled within a single batch mean gradient. We introduce MAGIA a momentum based adaptive correction on…
Image ReconstructionProvable Sparse Inversion and Token Relabel Enhanced One-shot Federated Learning with ViTs
One-Shot Federated Learning, where a central server learns a global model in a single communication round, has emerged as a promising paradigm. However, under extremely non-IID settings, existing data-free methods often …
Federated Learning