activity
20182024
most citedDefending Model Inversion and Membership Inference Attacks via Prediction Purification

50 citations · 182 across the 13 of their papers we have counts for

collaborators
Showing 2019Show all

5 papers · 1 filter

cs.CR2019

Self-Expiring Data Capsule using Trusted Execution Environment

Hung Dang, Ee-Chien Chang

Data privacy is unarguably of extreme importance. Nonetheless, there exist various daunting challenges to safe-guarding data privacy. These challenges stem from the fact that data…

cs.CR201924 cited

Effectiveness of Distillation Attack and Countermeasure on Neural Network Watermarking

Ziqi Yang, Hung Dang, Ee-Chien Chang

The rise of machine learning as a service and model sharing platforms has raised the need of traitor-tracing the models and proof of authorship. Watermarking technique is the main…

cs.LG2019

Enhancing Transformation-based Defenses using a Distribution Classifier

Connie Kou, Hwee Kuan Lee, Ee-Chien Chang +1

Adversarial attacks on convolutional neural networks (CNN) have gained significant attention and there have been active research efforts on defense mechanisms. Stochastic input tra…

cs.DC20192 cited

Autonomous Membership Service for Enclave Applications

Hung Dang, Ee-Chien Chang

Trusted Execution Environment, or enclave, promises to protect data confidentiality and execution integrity of an outsourced computation on an untrusted host. Extending the protect…

cs.CR201925 cited

Adversarial Neural Network Inversion via Auxiliary Knowledge Alignment

Ziqi Yang, Ee-Chien Chang, Zhenkai Liang

The rise of deep learning technique has raised new privacy concerns about the training data and test data. In this work, we investigate the model inversion problem in the adversari…