6 papers
AskBeacon -- Performing genomic data exchange and analytics with natural language
Anuradha Wickramarachchi, Shakila Tonni, Sonali Majumdar +7
Enabling clinicians and researchers to directly interact with global genomic data resources by removing technological barriers is vital for medical genomics. AskBeacon enables Larg…
Graded Suspiciousness of Adversarial Texts to Human
Shakila Mahjabin Tonni, Pedro Faustini, Mark Dras
Adversarial examples pose a significant challenge to deep neural networks (DNNs) across both image and text domains, with the intent to degrade model performance through meticulous…
IDT: Dual-Task Adversarial Attacks for Privacy Protection
Pedro Faustini, Shakila Mahjabin Tonni, Annabelle McIver +2
Natural language processing (NLP) models may leak private information in different ways, including membership inference, reconstruction or attribute inference attacks. Sensitive in…
What Learned Representations and Influence Functions Can Tell Us About Adversarial Examples
Shakila Mahjabin Tonni, Mark Dras
Adversarial examples, deliberately crafted using small perturbations to fool deep neural networks, were first studied in image processing and more recently in NLP. While approaches…
Directional Privacy for Deep Learning
Pedro Faustini, Natasha Fernandes, Shakila Tonni +2
Differentially Private Stochastic Gradient Descent (DP-SGD) is a key method for applying privacy in the training of deep learning models. It applies isotropic Gaussian noise to gra…
Data and Model Dependencies of Membership Inference Attack
Shakila Mahjabin Tonni, Dinusha Vatsalan, Farhad Farokhi +3
Machine learning (ML) models have been shown to be vulnerable to Membership Inference Attacks (MIA), which infer the membership of a given data point in the target dataset by obser…