Deep-Lock: Secure Authorization for Deep Neural Networks
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2020
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909111086481408 |
|---|---|
| author | Alam, Manaar Saha, Sayandeep Mukhopadhyay, Debdeep Kundu, Sandip |
| author_facet | Alam, Manaar Saha, Sayandeep Mukhopadhyay, Debdeep Kundu, Sandip |
| contents | Trained Deep Neural Network (DNN) models are considered valuable Intellectual Properties (IP) in several business models. Prevention of IP theft and unauthorized usage of such DNN models has been raised as of significant concern by industry. In this paper, we address the problem of preventing unauthorized usage of DNN models by proposing a generic and lightweight key-based model-locking scheme, which ensures that a locked model functions correctly only upon applying the correct secret key. The proposed scheme, known as Deep-Lock, utilizes S-Boxes with good security properties to encrypt each parameter of a trained DNN model with secret keys generated from a master key via a key scheduling algorithm. The resulting dense network of encrypted weights is found robust against model fine-tuning attacks. Finally, Deep-Lock does not require any intervention in the structure and training of the DNN models, making it applicable for all existing software and hardware implementations of DNN. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2008_05966 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | Deep-Lock: Secure Authorization for Deep Neural Networks Alam, Manaar Saha, Sayandeep Mukhopadhyay, Debdeep Kundu, Sandip Machine Learning Cryptography and Security Trained Deep Neural Network (DNN) models are considered valuable Intellectual Properties (IP) in several business models. Prevention of IP theft and unauthorized usage of such DNN models has been raised as of significant concern by industry. In this paper, we address the problem of preventing unauthorized usage of DNN models by proposing a generic and lightweight key-based model-locking scheme, which ensures that a locked model functions correctly only upon applying the correct secret key. The proposed scheme, known as Deep-Lock, utilizes S-Boxes with good security properties to encrypt each parameter of a trained DNN model with secret keys generated from a master key via a key scheduling algorithm. The resulting dense network of encrypted weights is found robust against model fine-tuning attacks. Finally, Deep-Lock does not require any intervention in the structure and training of the DNN models, making it applicable for all existing software and hardware implementations of DNN. |
| title | Deep-Lock: Secure Authorization for Deep Neural Networks |
| topic | Machine Learning Cryptography and Security |
| url | https://arxiv.org/abs/2008.05966 |