NeuronSig: A general adversarial attack detector based on neuron signature of deep neural network

This publication has 8 references indexed in Scilit:

• ADS-detector: An attention-based dual stream adversarial example detection method
  Knowledge-Based Systems, 2023
• Query-Efficient Black-Box Adversarial Attacks Guided by a Transfer-Based Prior
  IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
• Multimodal Neurons in Artificial Neural Networks
  Distill, 2021
• Deep neural rejection against adversarial examples
  EURASIP Journal on Information Security, 2020
• Adversarial Attacks on Deep-learning Models in Natural Language Processing
  ACM Transactions on Intelligent Systems and Technology, 2020
• Review of Artificial Intelligence Adversarial Attack and Defense Technologies
  Applied Sciences, 2019
• One Pixel Attack for Fooling Deep Neural Networks
  IEEE Transactions on Evolutionary Computation, 2019
• Automatic autonomous vision-based power line inspection: A review of current status and the potential role of deep learning
  International Journal of Electrical Power & Energy Systems, 2018