Gradient leakage attacks on GNNs for netlist benchmarks can expose gate types and Trojan properties; attention-based models leak more while defenses like differential privacy help only in limited cases without full performance preservation.
A survey on gradient inversion: Attacks, defenses and future directions,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Leaking Circuit Secrets: Gradient Leakage Attacks on Graph Neural Networks
Gradient leakage attacks on GNNs for netlist benchmarks can expose gate types and Trojan properties; attention-based models leak more while defenses like differential privacy help only in limited cases without full performance preservation.