Towards Adversarial Purification using Denoising AutoEncoders
Authors: Dvij Kalaria, Aritra Hazra, Partha Pratim Chakrabarti | Published: 2022-08-29
DNN IP Protection Method
DNNShield: Dynamic Randomized Model Sparsification, A Defense Against Adversarial Machine Learning
Authors: Mohammad Hossein Samavatian, Saikat Majumdar, Kristin Barber, Radu Teodorescu | Published: 2022-07-31
DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardware
Authors: Hanieh Hashemi, Yongqin Wang, Murali Annavaram | Published: 2022-06-30
Matryoshka: Stealing Functionality of Private ML Data by Hiding Models in Model
Authors: Xudong Pan, Yifan Yan, Shengyao Zhang, Mi Zhang, Min Yang | Published: 2022-06-29
ROSE: A RObust and SEcure DNN Watermarking
Authors: Kassem Kallas, Teddy Furon | Published: 2022-06-22
Deep Quaternion Features for Privacy Protection
Authors: Hao Zhang, Yiting Chen, Liyao Xiang, Haotian Ma, Jie Shi, Quanshi Zhang | Published: 2020-03-18 | Updated: 2020-06-21
Entangled Watermarks as a Defense against Model Extraction
Authors: Hengrui Jia, Christopher A. Choquette-Choo, Varun Chandrasekaran, Nicolas Papernot | Published: 2020-02-27 | Updated: 2021-02-19
Stealing Knowledge from Protected Deep Neural Networks Using Composite Unlabeled Data
Authors: Itay Mosafi, Eli David, Nathan S. Netanyahu | Published: 2019-12-09
MimosaNet: An Unrobust Neural Network Preventing Model Stealing
Authors: Kálmán Szentannai, Jalal Al-Afandi, András Horváth | Published: 2019-07-02
On the Robustness of the Backdoor-based Watermarking in Deep Neural Networks
Authors: Masoumeh Shafieinejad, Jiaqi Wang, Nils Lukas, Xinda Li, Florian Kerschbaum | Published: 2019-06-18 | Updated: 2019-11-26