High-Fidelity Extraction of Neural Network Models

By Matthew Jagielski, Nicholas Carlini, David Berthelot, Alexey Kurakin, Nicolas Papernot. 2019

36 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Kalpesh Krishna
2. Mohit Iyyer
3. Yonatan Belinkov
4. Eric Wallace
5. Ankur P. Parikh
6. Gaurav Singh Tomar
7. Hengrui Jia
8. Christopher A. Choquette-Choo

Citations in the corpus

• Thieves on Sesame Street! Model Extraction of BERT-based APIs (2019, result): “…models contrasts with prior work, where large-scale attacks require at minimum that the adversary can access a small amount of semantically-coherent data relevant to the task (Papernot et al., 2017; Correia-Silva et al., 2018; Orekondy et al., 2019a; Pal et al., 2019; Jagielski et al., 2019).”
• Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks (2019, unknown): “Jagielski et al. (2019) CNN* Unlabeled Data 3 - - - - 14.”
• Entangled Watermarks as a Defense against Model Extraction (2020, background): “Identifying whether two ML models are identical (in the sense that they have the same decision function) is fundamentally hard and can be reduced to an NP-hard problem [15].”