Abstract: In recent years,deep learning is widely used in the field of computer vision and has achieved outstanding success.However,the researchers found that the neural network is easily disturbed by adding subtle perturbations in the dataset,that can cause the model to give incorrect outputs.Such input examples are called “adversarial examples”.At present,a series of algorithms for generating adversarial examples have emerged.Based on the existing adversarial sample generation algorithm－projected gradient descent(PGD),this paper proposes an improved method－MPGD_CW algorithm,which combines momentum and adopts a new loss function to ensure the stability of the update direction and avoid bad local maximums.At the same time,it can avoid the disappearance of the gradient by replacing the cross-entropy loss function.Experiments on 4 robust models containing 3 architecturesconfirm that the proposed MPGD_CW algorithm has better attack effect and stronger transfer attack capacity.

Key words: Adversarial attacks, Convolutional neural network, Deep learning, Image adversarial examples