Certified Robustness Against Natural Language Attacks by Causal Intervention.
Haiteng ZhaoChang MaXinshuai DongAnh Tuan LuuZhi-Hong DengHanwang ZhangPublished in: ICML (2022)
Keyphrases
- natural language
- digital image watermarking
- semi fragile watermarking
- natural language processing
- semantic analysis
- knowledge representation
- countermeasures
- geometric attacks
- image watermarking scheme
- machine learning
- traffic analysis
- natural language interface
- dialogue system
- language processing
- causal relationships
- natural language generation
- causal reasoning
- watermark embedding
- neural network
- natural language understanding
- security threats
- conceptual graphs
- watermarking scheme
- bayesian networks