Search Results for author:
Found 3 papers, 2 papers with code
Distribution-aware Fairness Test Generation
We found that images generated by DistroFair are 80% as realistic as real-world images.
Astraea: Grammar-based Fairness Testing
We propose a grammar-based fairness testing approach (called ASTRAEA) which leverages context-free grammars to generate discriminatory inputs that reveal fairness violations in software systems.
Towards Backdoor Attacks and Defense in Robust Machine Learning Models
Specifically, given a robust Deep Neural Network (DNN) that is trained using PGD-based first-order adversarial training approach, AEGIS uses feature clustering to effectively detect whether such DNNs are backdoor-infected or clean.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
