Knockoff Nets: Stealing Functionality of Black-Box Models
(CVPR) Ask to what extent can an adversary steal functionality of such "victim" models based solely on blackbox interactions: image in, predictions out.
- from
- Audit Algorithms
- added
- 2026-10-10
- likes
- 0
similar
-
Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Data arxiv.org
(IJCNN) (Code) Stealing black-box models (CNNs) knowledge by querying them with random natural images (ImageNet and Microsoft-COCO).
-
Data driven exploratory attacks on black box classifiers in adversarial domains sciencedirect.com
(Neurocomputing) Reverse engineers remote classifier models (e.g., for evading a CAPTCHA test).
-
Black-Box Ripper: Copying black-box models using generative evolutionary algorithms proceedings.neurips.cc
(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).
-
Stealing Neural Networks via Timing Side Channels arxiv.org
(arXiv) Stealing/approximating a model through timing attacks usin queries.
-
Making targeted black-box evasion attacks effective andefficient arxiv.org
(arXiv) Investigates how an adversary can optimally use its query budget for targeted evasion attacks against deep neural networks.
-
Under manipulations, are some AI models harder to audit? grodino.github.io
(SATML) Relates the difficulty of black-box audits to the capacity of the targeted models, using the Rademacher complexity.
Audit Algorithms › Papers > 2019: “(CVPR) Ask to what extent can an adversary steal functionality of such "victim" models based solely on blackbox interactions: image in, predictions out.”