76 citations · 105 across the 12 of their papers we have counts for
12 papers
Differential Aggregation against General Colluding Attackers
Rong Du, Qingqing Ye, Yue Fu +4
Local Differential Privacy (LDP) is now widely adopted in large-scale systems to collect and analyze sensitive data while preserving users' privacy. However, almost all LDP protoco…
Repairing Adversarial Texts through Perturbation
Guoliang Dong, Jingyi Wang, Jun Sun +5
It is known that neural networks are subject to attacks through adversarial perturbations, i.e., inputs which are maliciously crafted through perturbations to induce wrong predicti…
A Unified Game-Theoretic Interpretation of Adversarial Robustness
Jie Ren, Die Zhang, Yisen Wang +8
This paper provides a unified view to explain different adversarial attacks and defense methods, \emph{i.e.} the view of multi-order interactions between input variables of DNNs. B…
Backdoor Pre-trained Models Can Transfer to All
Lujia Shen, Shouling Ji, Xuhong Zhang +6
Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model wit…
Thief, Beware of What Get You There: Towards Understanding Model Extraction Attack
Xinyi Zhang, Chengfang Fang, Jie Shi
Model extraction increasingly attracts research attentions as keeping commercial AI models private can retain a competitive advantage. In some scenarios, AI models are trained prop…
A-FMI: Learning Attributions from Deep Networks via Feature Map Importance
An Zhang, Xiang Wang, Chengfang Fang +3
Gradient-based attribution methods can aid in the understanding of convolutional neural networks (CNNs). However, the redundancy of attribution features and the gradient saturation…
DAFAR: Defending against Adversaries by Feedback-Autoencoder Reconstruction
Haowen Liu, Ping Yi, Hsiao-Ying Lin +2
Deep learning has shown impressive performance on challenging perceptual tasks and has been widely used in software to provide intelligent services. However, researchers found deep…
A Unified Game-Theoretic Interpretation of Adversarial Robustness
Jie Ren, Die Zhang, Yisen Wang +8
This paper provides a unified view to explain different adversarial attacks and defense methods, i.e. the view of multi-order interactions between input variables of DNNs. Based on…
Rethinking Natural Adversarial Examples for Classification Models
Xiao Li, Jianmin Li, Ting Dai +3
Recently, it was found that many real-world examples without intentional modifications can fool machine learning models, and such examples are called "natural adversarial examples"…
Where Does the Robustness Come from? A Study of the Transformation-based Ensemble Defence
Chang Liao, Yao Cheng, Chengfang Fang +1
This paper aims to provide a thorough study on the effectiveness of the transformation-based ensemble defence for image classification and its reasons. It has been empirically show…
Rotation-Equivariant Neural Networks for Privacy Protection
Hao Zhang, Yiting Chen, Haotian Ma +5
In order to prevent leaking input information from intermediate-layer features, this paper proposes a method to revise the traditional neural network into the rotation-equivariant…
Deep Quaternion Features for Privacy Protection
Hao Zhang, Yiting Chen, Liyao Xiang +3
We propose a method to revise the neural network to construct the quaternion-valued neural network (QNN), in order to prevent intermediate-layer features from leaking input informa…