Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models.
Shawn ShanWenxin DingJosephine PassanantiHaitao ZhengBen Y. ZhaoPublished in: CoRR (2023)
Keyphrases
- generative model
- bayesian framework
- input image
- image features
- image segmentation
- multiscale
- image retrieval
- image content
- mixture model
- image representation
- probabilistic model
- image classification
- discriminative models
- prior knowledge
- information retrieval
- visual patterns
- em algorithm
- semi supervised
- machine learning
- expectation maximization
- keypoints
- conditional random fields
- text classification
- image set
- clustering algorithm