Don't be a Fool: Pooling Strategies in Offensive Language Detection from User-Intended Adversarial Attacks.
Seunguk YuJuhwan ChoiYoungbin KimPublished in: CoRR (2024)
Keyphrases
- social networks
- malicious users
- detection method
- user interface
- automatic detection
- object detection
- language learning
- attack detection
- detection accuracy
- detection algorithm
- user interaction
- end users
- natural language
- anomaly detection
- user preferences
- user experience
- programming language
- false alarms
- countermeasures
- detecting malicious
- normal behavior
- multi agent