The paper introduces a framework of four complementary analyses to evaluate the faithfulness of synthetic concept images from zero-shot T2I models versus real images for concept-based XAI.
Very deep convo- lutional networks for large-scale image recognition
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
representative citing papers
Random parameter pruning during targeted attack optimization on surrogate models yields up to 11.7% higher average attack success rates when transferring to Transformer targets.
citing papers explorer
-
A Framework for Evaluating Zero-Shot Image Generation in Concept-based Explainability
The paper introduces a framework of four complementary analyses to evaluate the faithfulness of synthetic concept images from zero-shot T2I models versus real images for concept-based XAI.
-
RaPA: Enhancing Transferable Targeted Attacks via Random Parameter Pruning
Random parameter pruning during targeted attack optimization on surrogate models yields up to 11.7% higher average attack success rates when transferring to Transformer targets.