Privacy Attacks Against Biometric Models with Fewer Samples: Incorporating the Output of Multiple Models
Authors: Sohaib Ahmad, Benjamin Fuller, Kaleel Mahmood | Published: 2022-09-22
モデル抽出攻撃
Dataset Inference for Self-Supervised Models
Authors: Adam Dziedzic, Haonan Duan, Muhammad Ahmad Kaleem, Nikita Dhawan, Jonas Guan, Yannis Cattan, Franziska Boenisch, Nicolas Papernot | Published: 2022-09-16 | Updated: 2023-01-13
SEEK: model extraction attack against hybrid secure inference protocols
Authors: Si Chen, Junfeng Fan | Published: 2022-09-14
Stealing and Evading Malware Classifiers and Antivirus at Low False Positive Conditions
Authors: Maria Rigaki, Sebastian Garcia | Published: 2022-04-13 | Updated: 2023-06-04
Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs
Authors: Qiongkai Xu, Xuanli He, Lingjuan Lyu, Lizhen Qu, Gholamreza Haffari | Published: 2021-08-29 | Updated: 2022-09-04
Stateful Detection of Model Extraction Attacks
Authors: Soham Pal, Yash Gupta, Aditya Kanade, Shirish Shevade | Published: 2021-07-12
A Review of Confidentiality Threats Against Embedded Neural Network Models
Authors: Raphaël Joud, Pierre-Alain Moellic, Rémi Bernhard, Jean-Baptiste Rigaud | Published: 2021-05-04
Model extraction from counterfactual explanations
Authors: Ulrich Aïvodji, Alexandre Bolot, Sébastien Gambs | Published: 2020-09-03
High Accuracy and High Fidelity Extraction of Neural Networks
Authors: Matthew Jagielski, Nicholas Carlini, David Berthelot, Alex Kurakin, Nicolas Papernot | Published: 2019-09-03 | Updated: 2020-03-03
The advantages of multiple classes for reducing overfitting from test set reuse
Authors: Vitaly Feldman, Roy Frostig, Moritz Hardt | Published: 2019-05-24