activity
20182022
most citedResurrecting Trust in Facial Recognition: Mitigating Backdoor Attacks in Face Recognition to Prevent Potential Privacy Breaches

2 citations · 2 across the 1 of their papers we have counts for

collaborators

8 papers

cs.CV20222 cited

Resurrecting Trust in Facial Recognition: Mitigating Backdoor Attacks in Face Recognition to Prevent Potential Privacy Breaches

Reena Zelenkova, Jack Swallow, M. A. P. Chamikara +5

Biometric data, such as face images, are often associated with sensitive information (e.g medical, financial, personal government records). Hence, a data breach in a system storing…

cs.CV2021

Robust Training Using Natural Transformation

Shuo Wang, Lingjuan Lyu, Surya Nepal +3

Previous robustness approaches for deep learning models such as data augmentation techniques via data transformation or adversarial training cannot capture real-world variations th…

cs.LG2020

Defending Adversarial Attacks via Semantic Feature Manipulation

Shuo Wang, Tianle Chen, Surya Nepal +3

Machine learning models have demonstrated vulnerability to adversarial attacks, more specifically misclassification of adversarial examples. In this paper, we propose a one-off and…

cs.LG2020

OIAD: One-for-all Image Anomaly Detection with Disentanglement Learning

Shuo Wang, Tianle Chen, Shangyu Chen +3

Anomaly detection aims to recognize samples with anomalous and unusual patterns with respect to a set of normal data. This is significant for numerous domain applications, such as…

cs.LG2020

Backdoor Attacks against Transfer Learning with Pre-trained Deep Learning Models

Shuo Wang, Surya Nepal, Carsten Rudolph +3

Transfer learning provides an effective solution for feasibly and fast customize accurate \textit{Student} models, by transferring the learned knowledge of pre-trained \textit{Teac…

cs.CR2018

A model for system developers to measure the privacy risk of data

Awanthika Senarath, Marthie Grobler, Nalin Asanka Gamagedara Arachchilage

In this paper, we propose a model that could be used by system developers to measure the privacy risk perceived by users when they disclose data into software systems. We first der…