277 citations · 582 across the 16 of their papers we have counts for
17 papers
Deep Unlearn: Benchmarking Machine Unlearning for Image Classification
Xavier F. Cadet, Anastasia Borovykh, Mohammad Malekzadeh +2
Machine unlearning (MU) aims to remove the influence of particular data points from the learnable parameters of a trained machine learning model. This is a crucial capability in li…
CroSSL: Cross-modal Self-Supervised Learning for Time-series through Latent Masking
Shohreh Deldari, Dimitris Spathis, Mohammad Malekzadeh +3
Limited availability of labeled data for machine learning on multimodal time-series extensively hampers progress in the field. Self-supervised learning (SSL) is a promising approac…
Vicious Classifiers: Assessing Inference-time Data Reconstruction Risk in Edge Computing
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 and only share the models o…
Enhancing Efficiency in Multidevice Federated Learning through Data Selection
Fan Mo, Mohammad Malekzadeh, Soumyajit Chatterjee +2
Ubiquitous wearable and mobile devices provide access to a diverse set of data. However, the mobility demand for our devices naturally imposes constraints on their computational an…
Efficient Hyperparameter Optimization for Differentially Private Deep Learning
Aman Priyanshu, Rakshit Naidu, Fatemehsadat Mireshghallah +1
Tuning the hyperparameters in the differentially private stochastic gradient descent (DPSGD) is a fundamental challenge. Unlike the typical SGD, private datasets cannot be used man…
Quantifying and Localizing Usable Information Leakage from Neural Network Gradients
Fan Mo, Anastasia Borovykh, Mohammad Malekzadeh +3
In collaborative learning, clients keep their data private and communicate only the computed gradients of the deep neural network being trained on their local data. Several recent…
Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs
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 repre…
Dopamine: Differentially Private Federated Learning on Medical Data
Mohammad Malekzadeh, Burak Hasircioglu, Nitish Mital +3
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 (…
Layer-wise Characterization of Latent Information Leakage in Federated Learning
Fan Mo, Anastasia Borovykh, Mohammad Malekzadeh +2
Training deep neural networks via federated learning allows clients to share, instead of the original data, only the model trained on their data. Prior work has demonstrated that i…
Running Neural Networks on the NIC
Giuseppe Siracusano, Salvator Galea, Davide Sanvito +4
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…
DANA: Dimension-Adaptive Neural Architecture for Multivariate Sensor Data
Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro +1
Motion sensors embedded in wearable and mobile devices allow for dynamic selection of sensor streams and sampling rates, enabling several applications, such as power management and…
Privacy and Utility Preserving Sensor-Data Transformations
Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro +1
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. To…
Privacy-Preserving Bandits
Mohammad Malekzadeh, Dimitrios Athanasakis, Hamed Haddadi +1
Contextual bandit algorithms~(CBAs) often rely on personal data to provide recommendations. Centralized CBA agents utilize potentially sensitive data from recent interactions to pr…
Modeling and Forecasting Art Movements with CGANs
Edoardo Lisi, Mohammad Malekzadeh, Hamed Haddadi +2
Conditional Generative Adversarial Networks~(CGAN) are a recent and popular method for generating samples from a probability distribution conditioned on latent information. The lat…
Mobile Sensor Data Anonymization
Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro +1
Motion sensors such as accelerometers and gyroscopes measure the instant acceleration and rotation of a device, in three dimensions. Raw data streams from motion sensors embedded i…
Protecting Sensory Data against Sensitive Inferences
Mohammad Malekzadeh, Richard G. Clegg, Andrea Cavallaro +1
There is growing concern about how personal data are used when users grant applications direct access to the sensors of their mobile devices. In fact, high resolution temporal data…
Replacement AutoEncoder: A Privacy-Preserving Algorithm for Sensory Data Analysis
Mohammad Malekzadeh, Richard G. Clegg, Hamed Haddadi
An increasing number of sensors on mobile, Internet of things (IoT), and wearable devices generate time-series measurements of physical activities. Though access to the sensory dat…