67 citations · 198 across the 24 of their papers we have counts for
12 papers · 1 filter
Low-Rank Multitask Learning based on Tensorized SVMs and LSSVMs
Jiani Liu, Qinghua Tao, Ce Zhu +3
Multitask learning (MTL) leverages task-relatedness to enhance performance. With the emergence of multimodal data, tasks can now be referenced by multiple indices. In this paper, w…
Investigating Catastrophic Overfitting in Fast Adversarial Training: A Self-fitting Perspective
Zhengbao He, Tao Li, Sizhe Chen +1
Although fast adversarial training provides an efficient approach for building robust networks, it may suffer from a serious problem known as catastrophic overfitting (CO), where m…
Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors
Sizhe Chen, Geng Yuan, Xinwen Cheng +4
As data becomes increasingly vital, a company would be very cautious about releasing data, because the competitors could use it to train high-performance models, thereby posing a t…
Multi-head Ensemble of Smoothed Classifiers for Certified Robustness
Kun Fang, Qinghua Tao, Yingwen Wu +3
Randomized Smoothing (RS) is a promising technique for certified robustness, and recently in RS the ensemble of multiple Deep Neural Networks (DNNs) has shown state-of-the-art perf…
One-Pixel Shortcut: on the Learning Preference of Deep Neural Networks
Shutong Wu, Sizhe Chen, Cihang Xie +1
Unlearnable examples (ULEs) aim to protect data from unauthorized usage for training DNNs. Existing work adds -bounded perturbations to the original sample so that the…
Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks
Sizhe Chen, Zhehao Huang, Qinghua Tao +3
The score-based query attacks (SQAs) pose practical threats to deep neural networks by crafting adversarial perturbations within dozens of queries, only using the model's output sc…
Query Attack by Multi-Identity Surrogates
Sizhe Chen, Zhehao Huang, Qinghua Tao +1
Deep Neural Networks (DNNs) are acknowledged as vulnerable to adversarial attacks, while the existing black-box attacks require extensive queries on the victim DNN to achieve high…
Adversarial Attack Type I: Cheat Classifiers by Significant Changes
Sanli Tang, Xiaolin Huang, Mingjian Chen +2
Despite the great success of deep neural networks, the adversarial attack can cheat some well-trained classifiers by small permutations. In this paper, we propose another type of a…
Learning Data-adaptive Nonparametric Kernels
Fanghui Liu, Xiaolin Huang, Chen Gong +2
In this paper, we propose a data-adaptive non-parametric kernel learning framework in margin based kernel methods. In model formulation, given an initial kernel matrix, a data-adap…
Indefinite Kernel Logistic Regression with Concave-inexact-convex Procedure
Fanghui Liu, Xiaolin Huang, Chen Gong +2
In kernel methods, the kernels are often required to be positive definite, which restricts the use of many indefinite kernels. To consider those non-positive definite kernels, in t…
Nonconvex penalties with analytical solutions for one-bit compressive sensing
Xiaolin Huang, Ming Yan
One-bit measurements widely exist in the real world, and they can be used to recover sparse signals. This task is known as the problem of learning halfspaces in learning theory and…
Online Robust Principal Component Analysis with Change Point Detection
Wei Xiao, Xiaolin Huang, Jorge Silva +2
Robust PCA methods are typically batch algorithms which requires loading all observations into memory before processing. This makes them inefficient to process big data. In this pa…