Zobrazeno 1 - 10
of 353
pro vyhledávání: '"Ghodsi, Zahra"'
Training contemporary AI models requires investment in procuring learning data and computing resources, making the models intellectual property of the owners. Popular model watermarking solutions rely on key input triggers for detection; the keys hav
Externí odkaz:
http://arxiv.org/abs/2309.06779
Autor:
Almashaqbeh, Ghada, Ghodsi, Zahra
Federated learning enables users to collaboratively train a machine learning model over their private datasets. Secure aggregation protocols are employed to mitigate information leakage about the local datasets. This setup, however, still leaks the p
Externí odkaz:
http://arxiv.org/abs/2306.06825
In two-party machine learning prediction services, the client's goal is to query a remote server's trained machine learning model to perform neural network inference in some application domain. However, sensitive information can be obtained during th
Externí odkaz:
http://arxiv.org/abs/2207.07177
Autor:
Ghodsi, Zahra, Javaheripi, Mojan, Sheybani, Nojan, Zhang, Xinqiao, Huang, Ke, Koushanfar, Farinaz
Privacy-preserving federated learning allows multiple users to jointly train a model with coordination of a central server. The server only learns the final aggregation result, thus the users' (private) training data is not leaked from the individual
Externí odkaz:
http://arxiv.org/abs/2206.12100
Autor:
Baigi, Vali, Azadmanjir, Zahra, Khormali, Moein, Ghodsi, Zahra, Dashtkoohi, Mohammad, Sadeghi-Naini, Mohsen, Naghdi, Khatereh, Khazaeipour, Zahra, Abdi, Mahtab, Harrop, James S., Rahimi-Movaghar, Vafa
Publikováno v:
In World Neurosurgery September 2024 189:e177-e183
The privacy concerns of providing deep learning inference as a service have underscored the need for private inference (PI) protocols that protect users' data and the service provider's model using cryptographic methods. Recently proposed PI protocol
Externí odkaz:
http://arxiv.org/abs/2111.02583
Autor:
Jazayeri, Seyed Behnam, Maroufi, Seyed Farzad, Akbarinejad, Shaya, Ghodsi, Zahra, Rahimi-Movaghar, Vafa
Publikováno v:
In World Neurosurgery: X July 2024 23
Publikováno v:
IEEE Security & Privacy, vol. 20, no. 05, pp. 22-34, 2022
The emergence of deep learning has been accompanied by privacy concerns surrounding users' data and service providers' models. We focus on private inference (PI), where the goal is to perform inference on a user's data sample using a service provider
Externí odkaz:
http://arxiv.org/abs/2106.11755
The simultaneous rise of machine learning as a service and concerns over user privacy have increasingly motivated the need for private inference (PI). While recent work demonstrates PI is possible using cryptographic primitives, the computational ove
Externí odkaz:
http://arxiv.org/abs/2106.08475
Autor:
Azadmanjir, Zahra, Khormali, Moein, Sadeghi-Naini, Mohsen, Baigi, Vali, Pirnejad, Habibollah, Dashtkoohi, Mohammad, Ghodsi, Zahra, Jazayeri, Seyed Behnam, Shakeri, Aidin, Mohammadzadeh, Mahdi, Bagheri, Laleh, Lotfi, Mohammad-Sajjad, Daliri, Salman, Azarhomayoun, Amir, Sadeghi-Bazargani, Homayoun, O'reilly, Gerard, Rahimi-Movaghar, Vafa
Publikováno v:
In Chinese Journal of Traumatology May 2024 27(3):173-179