QUERY-EFFICIENT DECISION-BASED SPARSE ATTACKS AGAINST BLACK-BOX MACHINE LEARNING MODELS

no code implementations • ICLR 2022 • Viet Vo, Ehsan M Abbasnejad, Damith Ranasinghe

The ability to extract information from solely the output of a machine learning model to craft adversarial perturbations to black-box models is a practical threat against real-world systems, such as autonomous cars or machine learning models exposed as a service (MLaaS).

BIG-bench Machine Learning

Deep Auto-Set: A Deep Auto-Encoder-Set Network for Activity Recognition Using Wearables

no code implementations • 20 Nov 2018 • Alireza Abedin Varamin, Ehsan Abbasnejad, Qinfeng Shi, Damith Ranasinghe, Hamid Rezatofighi

Automatic recognition of human activities from time-series sensor data (referred to as HAR) is a growing area of research in ubiquitous computing.

Activity Recognition Multi-class Classification +2

Efficient Dense Labeling of Human Activity Sequences from Wearables using Fully Convolutional Networks

no code implementations • 20 Feb 2017 • Rui Yao, Guosheng Lin, Qinfeng Shi, Damith Ranasinghe

We conduct extensive experiments and demonstrate that our proposed approach is able to outperform the state-of-the-arts in terms of classification and label misalignment measures on three challenging datasets: Opportunity, Hand Gesture, and our new dataset.