Publications

G2Face: High-Fidelity Reversible Face Anonymization via Generative and Geometric Priors
Reversible face anonymization, unlike traditional face pixelization, seeks to replace sensitive identity information in facial images …
PDF Cite DOI
Federated Learning with Hybrid Knowledge Distillations on Long-Tailed Heterogeneous Client Data
Federated learning (FL) has a great potential in large-scale machine learning applications by training a global model over distributed …
PDF Cite Code
Deep Ensemble Robustness by Adaptive Sampling in Dropout-Based Simultaneous Training
Recent studies show that an ensemble of deep networks can have better adversarial robustness by increasing the learning diversity of …
PDF Cite DOI
Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation
Distilled student models in teacher-student architectures are widely considered for computational-effective deployment in real-time …
PDF Cite Code DOI
Disentanglement of Deep Features for Adversarial Face Detection
Existing adversarial face detectors are mostly developed against specific types of attacks, and limited by their generalizability …
PDF Cite DOI
Individual Property Inference Over Collaborative Learning in Deep Feature Space
Collaborative learning is used in multi-media applications to distribute computing tasks and data storage over multiple sites. Recent …
PDF Cite DOI
Improving Energy-Based Out-of-Distribution Detection by Sparsity Regularization
Out-of-distribution (OOD) detection is critical for safely deploying machine learning models in the open world. Recently, an …
PDF Cite Code DOI
A Smart Adversarial Attack on Deep Hashing Based Image Retrieval (Best Paper Award)
Deep hashing based retrieval models have been widely used in large-scale image retrieval systems. Recently, there has been a surging …
PDF Cite DOI
DAIR: A Query-Efficient Decision-based Attack on Image Retrieval Systems
There is an increasing interest in studying adversarial attacks on image retrieval systems. However, most of the existing attack …
PDF Cite DOI
Adversarial Defence by Diversified Simultaneous Training of Deep Ensembles
Learning-based classifiers are susceptible to adversarial examples. Existing defence methods are mostly devised on individual …
PDF Cite Code DOI
Decision-based Evasion Attacks on Tree Ensemble Classifiers
Learning-based classifiers are found to be susceptible to adversarial examples. Recent studies suggested that ensemble classifiers tend …
PDF Cite DOI
Group-Wise Dynamic Dropout Based on Latent Semantic Variations
Dropout regularization has been widely used in various deep neural networks to combat overfitting. It works by training a network to be …
PDF Cite DOI
GraphER: Token-Centric Entity Resolution with Graph Convolutional Neural Networks
Entity resolution (ER) aims to identify entity records that refer to the same real-world entity, which is a critical problem in data …
PDF Cite DOI
Model-Agnostic Adversarial Detection by Random Perturbations
Adversarial examples induce model classification errors on purpose, which has raised concerns on the security aspect of machine …
PDF Cite DOI
Cost-Sensitive Label Propagation for Semi-Supervised Face Recognition
In real-world applications, different kinds of learning and prediction errors are likely to incur different costs for the same system. …
PDF Cite DOI
Gradient Correlation: Are Ensemble Classifiers More Robust Against Evasion Attacks in Practical Settings?
Pattern recognition is an essential part of modern security systems for malware detection, intrusion detection, and spam filtering. …
PDF Cite DOI
Discriminative Latent Semantic Regression for Cross-Modal Hashing of Multimedia Retrieval
Due to large heterogeneity gaps between image, text, and video, finding content similarities of multimedia data is a challenging …
PDF Cite DOI
The PIT-trap—A “model-free” Bootstrap Procedure for Inference about Regression Models with Discrete, Multivariate Responses
Bootstrap methods are widely used in statistics, and bootstrapping of residuals can be especially useful in the regression context. …
PDF Cite DOI
Inference-based Similarity Search in Randomized Montgomery Domains for Privacy-preserving Biometric Identification
Similarity search is essential to many important applications and often involves searching at scale on high-dimensional data based on …
PDF Cite DOI
Learning Compact Binary Codes for Hash-Based Fingerprint Indexing
Compact binary codes can in general improve the speed of searches in large-scale applications. Although fingerprint retrieval was …
PDF Cite DOI
mvabund– an R package for model-based analysis of multivariate abundance data
Summary: 1. The mvabund package for R provides tools for model-based analysis of multivariate abundance data in ecology. 2. This …
PDF Cite Code DOI
Distance-based multivariate analyses confound location and dispersion effects
Summary: 1. A critical property of count data is its mean–variance relationship, yet this is rarely considered inmultivariate analysis …
PDF Cite DOI
Global Ridge Orientation Modeling for Partial Fingerprint Identification
Identifying incomplete or partial fingerprints from a large fingerprint database remains a difficult challenge today. Existing studies …
PDF Cite DOI
A Fingerprint Orientation Model Based on 2D Fourier Expansion (FOMFE) and Its Application to Singular-point Detection and Fingerprint Indexing
In this paper, we have proposed a fingerprint orientation model based on 2D Fourier expansions (FOMFE) in the phase plane. The FOMFE …
PDF Cite DOI