Login / Signup

An Interpretive Adversarial Attack Method: Attacking Softmax Gradient Layer-Wise Relevance Propagation Based on Cosine Similarity Constraint and TS-Invariant.

Zigang ChenRenjie DaiZhenghao LiuLong ChenYuhong LiuKai Sheng
Published in: Neural Process. Lett. (2023)
Keyphrases
  • cosine similarity
  • similarity measure
  • pairwise
  • similarity function
  • high level
  • unsupervised learning
  • clustering method