GeoDA: a geometric framework for black-box adversarial attacks

The Imitation Game: Algorithm Selectionby Exploiting Black-Box Recommender

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

Auditing radicalization pathways on

(FAT*) Studies the reachability of radical channels from each others, using random walks on static channel recommendations

Black-Box Ripper: Copying black-box models using generative evolutionary algorithms

(NeurIPS) Replicates the functionality of a black-box neural model, yet with no limit on the amount of queries (via a teacher/student scheme and an evolutionary search)

Remote Explainability faces the bouncer problem

(Nature Machine Intelligence volume 2, pages529–539) (Code) Shows the impossibility (with one request) or the difficulty to spot lies on the explanations of a remote AI decision