A data-free membership inference attack reconstructs images from federated learning updates using standard cell library layouts as priors, allowing inference of hardware characteristics such as circuit layers and technology nodes from reconstruction fidelity.
Deep leakage from gradients
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 1polarities
support 1representative citing papers
Federated learning improves segmentation accuracy for hardware reverse engineering but remains vulnerable to recovering proprietary SEM images via gradient inversion attacks.
BID-LoRA uses bi-directional low-rank adapters with retain/new/unlearn pathways and escape unlearning to enable continual learning and unlearning while minimizing knowledge leakage and parameter updates.
A local-training algorithm for nonconvex distributed optimization achieves communication efficiency and differential privacy via gradient clipping plus additive noise, with proven convergence to a stationary point within bounded distance and formal privacy guarantees.
Hybrid QFL cuts quantum transmissions from 3TNMP to {3t + 2(T-t)}NMP over T rounds while preserving near-centralized convergence and improving depolarizing-noise resilience via decentralized aggregation and Steane-code QEC.
Fed-Listing infers client label proportions in FedGNNs from final-layer gradients, outperforming baselines on four datasets and three architectures even in non-i.i.d. settings.
FedSpy-LLM uses gradient decomposition and iterative alignment to reconstruct larger batches and longer sequences of training data from LLM gradients in federated settings, including with PEFT methods.
citing papers explorer
-
A Data-Free Membership Inference Attack on Federated Learning in Hardware Assurance
A data-free membership inference attack reconstructs images from federated learning updates using standard cell library layouts as priors, allowing inference of hardware characteristics such as circuit layers and technology nodes from reconstruction fidelity.
-
Potentials and Pitfalls of Applying Federated Learning in Hardware Assurance
Federated learning improves segmentation accuracy for hardware reverse engineering but remains vulnerable to recovering proprietary SEM images via gradient inversion attacks.
-
BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning
BID-LoRA uses bi-directional low-rank adapters with retain/new/unlearn pathways and escape unlearning to enable continual learning and unlearning while minimizing knowledge leakage and parameter updates.
-
Communication-Efficient Distributed Learning with Differential Privacy
A local-training algorithm for nonconvex distributed optimization achieves communication efficiency and differential privacy via gradient clipping plus additive noise, with proven convergence to a stationary point within bounded distance and formal privacy guarantees.
-
Practical Quantum Federated Learning for Privacy-Sensitive Healthcare: Communication Efficiency and Noise Resilience
Hybrid QFL cuts quantum transmissions from 3TNMP to {3t + 2(T-t)}NMP over T rounds while preserving near-centralized convergence and improving depolarizing-noise resilience via decentralized aggregation and Steane-code QEC.
-
Fed-Listing: Federated Label Distribution Inference in Graph Neural Networks
Fed-Listing infers client label proportions in FedGNNs from final-layer gradients, outperforming baselines on four datasets and three architectures even in non-i.i.d. settings.
-
FedSpy-LLM: Towards Scalable and Generalizable Data Reconstruction Attacks from Gradients on LLMs
FedSpy-LLM uses gradient decomposition and iterative alignment to reconstruct larger batches and longer sequences of training data from LLM gradients in federated settings, including with PEFT methods.