Federated learning improves segmentation accuracy for hardware reverse engineering but remains vulnerable to recovering proprietary SEM images via gradient inversion attacks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.