86 citations · 255 across the 20 of their papers we have counts for
14 papers · 1 filter
Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks
Zhaohan Xi, Tianyu Du, Changjiang Li +5
Pre-trained language models (PLMs) have demonstrated remarkable performance as few-shot learners. However, their security risks under such settings are largely unexplored. In this…
On the Vulnerability of Backdoor Defenses for Federated Learning
Pei Fang, Jinghui Chen
Federated Learning (FL) is a popular distributed machine learning paradigm that enables jointly training a global model without sharing clients' data. However, its repetitive serve…
Spectral Augmentation for Self-Supervised Learning on Graphs
Lu Lin, Jinghui Chen, Hongning Wang
Graph contrastive learning (GCL), as an emerging self-supervised learning technique on graphs, aims to learn representations via instance discrimination. Its performance heavily re…
How Powerful is Implicit Denoising in Graph Neural Networks
Songtao Liu, Rex Ying, Hanze Dong +3
Graph Neural Networks (GNNs), which aggregate features from neighbors, are widely used for graph-structured data processing due to their powerful representation learning capabiliti…
One-shot Neural Backdoor Erasing via Adversarial Weight Masking
Shuwen Chai, Jinghui Chen
Recent studies show that despite achieving high accuracy on a number of real-world applications, deep neural networks (DNNs) can be backdoored: by injecting triggered data samples…
RoCourseNet: Distributionally Robust Training of a Prediction Aware Recourse Model
Hangzhi Guo, Feiran Jia, Jinghui Chen +2
Counterfactual (CF) explanations for machine learning (ML) models are preferred by end-users, as they explain the predictions of ML models by providing a recourse (or contrastive)…
Communication-Efficient Adaptive Federated Learning
Yujia Wang, Lu Lin, Jinghui Chen
Federated learning is a machine learning training paradigm that enables clients to jointly train models without sharing their own localized data. However, the implementation of fed…
Learnability Lock: Authorized Learnability Control Through Adversarial Invertible Transformations
Weiqi Peng, Jinghui Chen
Owing much to the revolution of information technology, the recent progress of deep learning benefits incredibly from the vastly enhanced access to data available in various digita…
Benign Overfitting in Adversarially Robust Linear Classification
Jinghui Chen, Yuan Cao, Quanquan Gu
"Benign overfitting", where classifiers memorize noisy training data yet still achieve a good generalization performance, has drawn great attention in the machine learning communit…
Efficient Robust Training via Backward Smoothing
Jinghui Chen, Yu Cheng, Zhe Gan +2
Adversarial training is so far the most effective strategy in defending against adversarial examples. However, it suffers from high computational costs due to the iterative adversa…
RayS: A Ray Searching Method for Hard-label Adversarial Attack
Jinghui Chen, Quanquan Gu
Deep neural networks are vulnerable to adversarial attacks. Among different attack settings, the most challenging yet the most practical one is the hard-label setting where the att…
Understanding the Intrinsic Robustness of Image Distributions using Conditional Generative Models
Xiao Zhang, Jinghui Chen, Quanquan Gu +1
Starting with Gilmer et al. (2018), several works have demonstrated the inevitability of adversarial examples based on different assumptions about the underlying input probability…
A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks
Jinghui Chen, Dongruo Zhou, Jinfeng Yi +1
Depending on how much information an adversary can access to, adversarial attacks can be classified as white-box attack and black-box attack. For white-box attack, optimization-bas…
Closing the Generalization Gap of Adaptive Gradient Methods in Training Deep Neural Networks
Jinghui Chen, Dongruo Zhou, Yiqi Tang +3
Adaptive gradient methods, which adopt historical gradient information to automatically adjust the learning rate, despite the nice property of fast convergence, have been observed…