Making targeted black-box evasion attacks effective andefficient
(arXiv) Investigates how an adversary can optimally use its query budget for targeted evasion attacks against deep neural networks.
- from
- Audit Algorithms
- added
- 2026-10-10
- likes
- 0
similar
-
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).
-
Knockoff Nets: Stealing Functionality of Black-Box Models arxiv.org
(CVPR) Ask to what extent can an adversary steal functionality of such "victim" models based solely on blackbox interactions: image in, predictions out.
-
GeoDA: a geometric framework for black-box adversarial attacks openaccess.thecvf.com
(CVPR) (Code) Crafts adversarial examples to fool models, in a pure blackbox setup (no gradients, inferred class only).
-
Neural Network Model Extraction Attacks in Edge Devicesby Hearing Architectural Hints arxiv.org
(arxiv) Through the acquisition of memory access events from bus snooping, layer sequence identification bythe LSTM-CTC model, layer topology connection according to the memory access pattern, and layer dimension estimation under data volume constraints, it demonstrates one can…
-
Stealing Neural Networks via Timing Side Channels arxiv.org
(arXiv) Stealing/approximating a model through timing attacks usin queries.
-
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).
Audit Algorithms › Papers > 2019: “(arXiv) Investigates how an adversary can optimally use its query budget for targeted evasion attacks against deep neural networks.”