Neural Network Model Extraction Attacks in Edge Devicesby Hearing Architectural Hints
(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…
- from
- Audit Algorithms
- added
- 2026-10-10
- likes
- 0
similar
-
Stealing Neural Networks via Timing Side Channels arxiv.org
(arXiv) Stealing/approximating a model through timing attacks usin queries.
-
TamperNN: Efficient Tampering Detection of Deployed Neural Nets arxiv.org
(ISSRE) Algorithms to craft inputs that can detect the tampering with a remotely executed classifier model.
-
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.
-
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.
-
Extracting Training Data from Large Language Models arxiv.org
(arxiv) Performs a training data extraction attack to recover individual training examples by querying the language model.
-
Adversarial Model Extraction on Graph Neural Networks arxiv.org
(AAAI Workshop on Deep Learning on Graphs: Methodologies and Applications) Introduces GNN model extraction and presents a preliminary approach for this.
Audit Algorithms › Papers > 2019: “(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…”