(arXiv) Stealing/approximating a model through timing attacks usin queries
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
(Harvard Journal of Law & Technology) To explain a decision on x, find a conterfactual: the closest point to x that changes the decision
(arXiv) Searches bias in the black box model by training an unsupervised implicit generative model. Thensummarizes the black-box model behavior quantitatively by perturbing data samples along the data manifold
(NIPS) Reversing graphs by observing some random walk commute times
(IJCNN) (Code) Stealing black-box models (CNNs) knowledge by querying them with random natural images (ImageNet and Microsoft-COCO)