Introduces Black-CL black-box benchmark and BETA textual-prototype method that matches or exceeds white-box continual learning performance on ten datasets using 0.05M parameters.
Black-box adversarial attack with transferable model-based embedding,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2roles
background 1polarities
background 1representative citing papers
NTGA is the first clean-label generalization attack under black-box settings but is vulnerable to adversarial training and image transformations, with newer attacks outperforming it.
citing papers explorer
-
Black-Box Continual Learning for Vision-Language Models
Introduces Black-CL black-box benchmark and BETA textual-prototype method that matches or exceeds white-box continual learning performance on ten datasets using 0.05M parameters.
-
SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions
NTGA is the first clean-label generalization attack under black-box settings but is vulnerable to adversarial training and image transformations, with newer attacks outperforming it.