Search Results for author: Mohammad Malekzadeh

Found 17 papers, 13 papers with code

Protecting Sensory Data against Sensitive Inferences

1 code implementation21 Feb 2018 Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro, Hamed Haddadi

Results show that the proposed framework maintains the usefulness of the transformed data for activity recognition, with an average loss of only around three percentage points, while reducing the possibility of gender classification to around 50\%, the target random guess, from more than 90\% when using raw sensor data.

Activity Recognition Attribute +2

Mobile Sensor Data Anonymization

1 code implementation26 Oct 2018 Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro, Hamed Haddadi

Motion sensors such as accelerometers and gyroscopes measure the instant acceleration and rotation of a device, in three dimensions.

Activity Recognition

Privacy and Utility Preserving Sensor-Data Transformations

1 code implementation14 Nov 2019 Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro, Hamed Haddadi

Sensitive inferences and user re-identification are major threats to privacy when raw sensor data from wearable or portable devices are shared with cloud-assisted applications.

Activity Recognition

DANA: Dimension-Adaptive Neural Architecture for Multivariate Sensor Data

2 code implementations5 Aug 2020 Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro, Hamed Haddadi

We introduce a dimension-adaptive pooling (DAP) layer that makes DNNs flexible and more robust to changes in sensor availability and in sampling rate.

Human Activity Recognition Imputation +1

Dopamine: Differentially Private Federated Learning on Medical Data

1 code implementation27 Jan 2021 Mohammad Malekzadeh, Burak Hasircioglu, Nitish Mital, Kunal Katarya, Mehmet Emre Ozfatura, Deniz Gündüz

While rich medical datasets are hosted in hospitals distributed across the world, concerns on patients' privacy is a barrier against using such data to train deep neural networks (DNNs) for medical diagnostics.

Federated Learning

Efficient Hyperparameter Optimization for Differentially Private Deep Learning

1 code implementation9 Aug 2021 Aman Priyanshu, Rakshit Naidu, FatemehSadat Mireshghallah, Mohammad Malekzadeh

Tuning the hyperparameters in the differentially private stochastic gradient descent (DPSGD) is a fundamental challenge.

Hyperparameter Optimization

Privacy-Preserving Bandits

1 code implementation10 Sep 2019 Mohammad Malekzadeh, Dimitrios Athanasakis, Hamed Haddadi, Benjamin Livshits

Contextual bandit algorithms~(CBAs) often rely on personal data to provide recommendations.

Multi-Label Classification Privacy Preserving

Replacement AutoEncoder: A Privacy-Preserving Algorithm for Sensory Data Analysis

1 code implementation18 Oct 2017 Mohammad Malekzadeh, Richard G. Clegg, Hamed Haddadi

Though access to the sensory data is critical to the success of many beneficial applications such as health monitoring or activity recognition, a wide range of potentially sensitive information about the individuals can also be discovered through access to sensory data and this cannot easily be protected using traditional privacy approaches.

Activity Recognition Privacy Preserving +2

Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs

1 code implementation25 May 2021 Mohammad Malekzadeh, Anastasia Borovykh, Deniz Gündüz

It is known that deep neural networks, trained for the classification of non-sensitive target attributes, can reveal sensitive attributes of their input data through internal representations extracted by the classifier.

Attribute Knowledge Distillation

Modeling and Forecasting Art Movements with CGANs

1 code implementation21 Jun 2019 Edoardo Lisi, Mohammad Malekzadeh, Hamed Haddadi, F. Din-Houn Lau, Seth Flaxman

Realisations from this distribution can be used by the CGAN to generate "future" paintings.

Vicious Classifiers: Data Reconstruction Attack at Inference Time

1 code implementation8 Dec 2022 Mohammad Malekzadeh, Deniz Gunduz

Privacy-preserving inference in edge computing paradigms encourages the users of machine-learning services to locally run a model on their private input, for a target task, and only share the model's outputs with the server.

Edge-computing Privacy Preserving +1

Salted Inference: Enhancing Privacy while Maintaining Efficiency of Split Inference in Mobile Computing

1 code implementation20 Oct 2023 Mohammad Malekzadeh, Fahim Kawsar

In split inference, a deep neural network (DNN) is partitioned to run the early part of the DNN at the edge and the later part of the DNN in the cloud.

Running Neural Networks on the NIC

no code implementations4 Sep 2020 Giuseppe Siracusano, Salvator Galea, Davide Sanvito, Mohammad Malekzadeh, Hamed Haddadi, Gianni Antichi, Roberto Bifulco

In this paper we show that the data plane of commodity programmable (Network Interface Cards) NICs can run neural network inference tasks required by packet monitoring applications, with low overhead.

BIG-bench Machine Learning

Layer-wise Characterization of Latent Information Leakage in Federated Learning

no code implementations17 Oct 2020 Fan Mo, Anastasia Borovykh, Mohammad Malekzadeh, Hamed Haddadi, Soteris Demetriou

Training deep neural networks via federated learning allows clients to share, instead of the original data, only the model trained on their data.

Federated Learning

Quantifying and Localizing Usable Information Leakage from Neural Network Gradients

no code implementations28 May 2021 Fan Mo, Anastasia Borovykh, Mohammad Malekzadeh, Soteris Demetriou, Deniz Gündüz, Hamed Haddadi

Our proposed framework enables clients to localize and quantify the private information leakage in a layer-wise manner, and enables a better understanding of the sources of information leakage in collaborative learning, which can be used by future studies to benchmark new attacks and defense mechanisms.

Attribute

Centaur: Federated Learning for Constrained Edge Devices

no code implementations8 Nov 2022 Fan Mo, Mohammad Malekzadeh, Soumyajit Chatterjee, Fahim Kawsar, Akhil Mathur

Federated learning (FL) facilitates new applications at the edge, especially for wearable and Internet-of-Thing devices.

Federated Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.