no code implementations • 4 Oct 2023 • Hassan Jameel Asghar, Zhigang Lu, Zhongrui Zhao, Dali Kaafar
In this work, we construct an interactive protocol for this problem based on the fully homomorphic encryption scheme over the Torus (TFHE) and label differential privacy, where the underlying machine learning model is a neural network.
no code implementations • 12 Apr 2023 • Gioacchino Tangari, Shreesh Keskar, Hassan Jameel Asghar, Dali Kaafar
For the biometric authentication use case, we need to investigate this under adversarial settings where an attacker has access to a feature-space representation but no direct access to the exact original dataset nor the original learned model.
no code implementations • 7 Dec 2022 • Benjamin Tag, Niels van Berkel, Sunny Verma, Benjamin Zi Hao Zhao, Shlomo Berkovsky, Dali Kaafar, Vassilis Kostakos, Olga Ohrimenko
Artificial Intelligence (AI) systems have been increasingly used to make decision-making processes faster, more accurate, and more efficient.
no code implementations • 4 Nov 2022 • Rana Salal Ali, Benjamin Zi Hao Zhao, Hassan Jameel Asghar, Tham Nguyen, Ian David Wood, Dali Kaafar
In this paper, we study the setting when NER models are available as a black-box service for identifying sensitive information in user documents and show that these models are vulnerable to membership inference on their training datasets.
1 code implementation • 17 Feb 2020 • Shakila Mahjabin Tonni, Dinusha Vatsalan, Farhad Farokhi, Dali Kaafar, Zhigang Lu, Gioacchino Tangari
Our results reveal the relationship between MIA accuracy and properties of the dataset and training model in use.
no code implementations • 2 Jun 2018 • Loqman Salamatian, Dali Kaafar, Kavé Salamatian
The monitoring of large dynamic networks is a major chal- lenge for a wide range of application.