2 papers
cs.HC2026
SketchXplain: Intuitive Visual Explanations of Image Classifiers with Sketches
Wencan Zhang, Mario Michelessa, Xuejun Zhao +1
Saliency map visualizations explain image-based AI predictions by pointing to regions, but these are often unintuitive and semantically unclear, leaving an interpretability gap. We…
cs.CV2021
Exploiting Explanations for Model Inversion Attacks
Xuejun Zhao, Wencan Zhang, Xiaokui Xiao +1
The successful deployment of artificial intelligence (AI) in many domains from healthcare to hiring requires their responsible use, particularly in model explanations and privacy.…