LLMPirate uses eight LLMs to rewrite Verilog netlists into functionally equivalent circuits that evade GNN4IP, MOSS, Jplag, and SIM on most tested designs.
Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions
1 Pith paper cite this work. Polarity classification is still indexing.
abstract
Despite its success in the image domain, adversarial training did not (yet) stand out as an effective defense for Graph Neural Networks (GNNs) against graph structure perturbations. In the pursuit of fixing adversarial training (1) we show and overcome fundamental theoretical as well as practical limitations of the adopted graph learning setting in prior work; (2) we reveal that more flexible GNNs based on learnable graph diffusion are able to adjust to adversarial perturbations, while the learned message passing scheme is naturally interpretable; (3) we introduce the first attack for structure perturbations that, while targeting multiple nodes at once, is capable of handling global (graph-level) as well as local (node-level) constraints. Including these contributions, we demonstrate that adversarial training is a state-of-the-art defense against adversarial structure perturbations.
fields
cs.CR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LLMPirate: LLMs for Black-box Hardware IP Piracy
LLMPirate uses eight LLMs to rewrite Verilog netlists into functionally equivalent circuits that evade GNN4IP, MOSS, Jplag, and SIM on most tested designs.