activity
20182022
most citedDarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments

190 citations · 295 across the 16 of their papers we have counts for

collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2022

Data augmentation with mixtures of max-entropy transformations for filling-level classification

Apostolos Modas, Andrea Cavallaro, Pascal Frossard

We address the problem of distribution shifts in test-time data with a principled data augmentation scheme for the task of content-level classification. In such a task, properties…

cs.LG2022

Is Cross-Attention Preferable to Self-Attention for Multi-Modal Emotion Recognition?

Vandana Rajan, Alessio Brutti, Andrea Cavallaro

Humans express their emotions via facial expressions, voice intonation and word choices. To infer the nature of the underlying emotion, recognition models may use a single modality…

cs.LG2020

Robust Latent Representations via Cross-Modal Translation and Alignment

Vandana Rajan, Alessio Brutti, Andrea Cavallaro

Multi-modal learning relates information across observation modalities of the same physical phenomenon to leverage complementary information. Most multi-modal machine learning meth…

cs.LG2020190 cited

DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments

Fan Mo, Ali Shahin Shamsabadi, Kleomenis Katevas +4

We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neur…

cs.LG2019

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…

cs.LG2019

EdgeFool: An Adversarial Image Enhancement Filter

Ali Shahin Shamsabadi, Changjae Oh, Andrea Cavallaro

Adversarial examples are intentionally perturbed images that mislead classifiers. These images can, however, be easily detected using denoising algorithms, when high-frequency spat…