"DANAA: Towards Transferable Attacks with Double Adversarial Neuron Att" by Zhibo Jin, Zhiyu Zhu et al.
While deep neural networks have excellent results in many fields, they are susceptible to interference from attacking samples resulting in erroneous judgments. Feature-level attacks are one of the effective attack types, which target the learned features in the hidden layers to improve their transferability across different models. Yet it is observed that the transferability has been largely impacted by the neuron importance estimation results. In this paper, a double adversarial neuron attribution attack method, termed ‘DANAA’, is proposed to obtain more accurate feature importance estima...
Source: uow.edu.au