activity
20162020
most citedGraph Neural Networks with Continual Learning for Fake News Detection from Social Media

78 citations · 83 across the 8 of their papers we have counts for

collaborators

8 papers

cs.LG20202 cited

Defending Distributed Classifiers Against Data Poisoning Attacks

Sandamal Weerasinghe, Tansu Alpcan, Sarah M. Erfani +1

Support Vector Machines (SVMs) are vulnerable to targeted training data manipulations such as poisoning attacks and label flips. By carefully manipulating a subset of training samp…

cs.LG20201 cited

Defending Regression Learners Against Poisoning Attacks

Sandamal Weerasinghe, Sarah M. Erfani, Tansu Alpcan +2

Regression models, which are widely used from engineering applications to financial forecasting, are vulnerable to targeted malicious attacks such as training data poisoning, throu…

cs.SI202078 cited

Graph Neural Networks with Continual Learning for Fake News Detection from Social Media

Yi Han, Shanika Karunasekera, Christopher Leckie

Although significant effort has been applied to fact-checking, the prevalence of fake news over social media, which has profound impact on justice, public trust and our society, re…

cs.LG2020

METEOR: Learning Memory and Time Efficient Representations from Multi-modal Data Streams

Amila Silva, Shanika Karunasekera, Christopher Leckie +1

Many learning tasks involve multi-modal data streams, where continuous data from different modes convey a comprehensive description about objects. A major challenge in this context…

cs.LG2020

Black-box Adversarial Example Generation with Normalizing Flows

Hadi M. Dolatabadi, Sarah Erfani, Christopher Leckie

Deep neural network classifiers suffer from adversarial vulnerability: well-crafted, unnoticeable changes to the input data can affect the classifier decision. In this regard, the…

cs.SI2020

Image Analysis Enhanced Event Detection from Geo-tagged Tweet Streams

Yi Han, Shanika Karunasekera, Christopher Leckie

Events detected from social media streams often include early signs of accidents, crimes or disasters. Therefore, they can be used by related parties for timely and efficient respo…