Zobrazeno 1 - 1
of 1
pro vyhledávání: '"Kriege, Nils N."'
Prior attacks on graph neural networks have mostly focused on graph poisoning and evasion, neglecting the network's weights and biases. Traditional weight-based fault injection attacks, such as bit flip attacks used for convolutional neural networks,
Externí odkaz:
http://arxiv.org/abs/2311.01205
