Sign in

No offence, Bert - I insult only humans! Multiple addressees sentence-level attack on toxicity detection neural network.

Sergey BerezinReza FarahbakhshNoël Crespi
Published in: CoRR (2023)
Keyphrases
  • sentence level
  • neural network
  • novelty detection
  • sentiment analysis
  • email
  • object detection
  • sentiment classification