← Search

N. Grace Hua

2 accepted papers

2023

Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation

ICLR 2023poster

Adversarial patch attacks are an emerging security threat for real world deep learning applications. We present Demasked Smoothing, the first approach (up to our knowledge) to certify the robustness of semantic segmentation models against this threat model. Previous work on certifiably defending aga…

Cited by 19SourcePDFScholar
2023

Identification of Systematic Errors of Image Classifiers on Rare Subgroups

ICCV 2023poster

Despite excellent average-case performance of many image classifiers, their performance can substantially deteriorate on semantically coherent subgroups of the data that were under-represented in the training data. These systematic errors can impact both fairness for demographic minority groups as w…

Cited by 22PDFScholar