Leo Yu Zhang | DeepAI

DeepAI AI Chat

Featured Co-authors

Wei Liu
370 publications
Jun Zhang
202 publications
Qian Wang
147 publications
Chao Chen
123 publications
Yong Wang
119 publications
Zhe Liu
107 publications
Junhui Hou
81 publications
Lichao Sun
67 publications
Hai Jin
35 publications
Zheng Yang
30 publications
Yong Xiang
29 publications

∙ 08/07/2023

A Four-Pronged Defense Against Byzantine Attacks in Federated Learning

Federated learning (FL) is a nascent distributed learning paradigm to tr...

0 Wei Wan, et al. ∙

∙ 07/23/2023

Downstream-agnostic Adversarial Examples

Self-supervised learning usually uses a large amount of unlabeled data t...

0 Ziqi Zhou, et al. ∙

∙ 07/15/2023

Why Does Little Robustness Help? Understanding Adversarial Transferability From Surrogate Training

Adversarial examples (AEs) for DNNs have been shown to be transferable: ...

0 Yechao Zhang, et al. ∙

∙ 06/27/2023

Catch Me If You Can: A New Low-Rate DDoS Attack Strategy Disguised by Feint

While collaborative systems provide convenience to our lives, they also ...

0 Tianyang Cai, et al. ∙

∙ 04/21/2023

Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learning

Federated learning (FL) is vulnerable to poisoning attacks, where advers...

0 Hangtao Zhang, et al. ∙

∙ 04/18/2023

Masked Language Model Based Textual Adversarial Example Detection

Adversarial attacks are a serious threat to the reliable deployment of m...

0 Xiaomei Zhang, et al. ∙

∙ 11/22/2022

PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples

Point cloud completion, as the upstream procedure of 3D recognition and ...

0 Shengshan Hu, et al. ∙

∙ 11/03/2022

M-to-N Backdoor Paradigm: A Stealthy and Fuzzy Attack to Deep Learning Models

Recent studies show that deep neural networks (DNNs) are vulnerable to b...

0 Linshan Hou, et al. ∙

∙ 10/04/2022

Shielding Federated Learning: Mitigating Byzantine Attacks with Less Constraints

Federated learning is a newly emerging distributed learning framework th...

0 Minghui Li, et al. ∙

∙ 07/01/2022

BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label

Due to its powerful feature learning capability and high efficiency, dee...

0 Shengshan Hu, et al. ∙

∙ 05/14/2022

Evaluating Membership Inference Through Adversarial Robustness

The usage of deep learning is being escalated in many applications. Due ...

0 Zhaoxi Zhang, et al. ∙

∙ 04/28/2022

Shielding Federated Learning: Robust Aggregation with Adaptive Client Selection

Federated learning (FL) enables multiple clients to collaboratively trai...

0 Wei Wan, et al. ∙

∙ 04/22/2022

Towards Privacy-Preserving Neural Architecture Search

Machine learning promotes the continuous development of signal processin...

0 Fuyi Wang, et al. ∙

∙ 04/05/2022

Attention Distraction: Watermark Removal Through Continual Learning with Selective Forgetting

Fine-tuning attacks are effective in removing the embedded watermarks in...

4 Qi Zhong, et al. ∙

∙ 03/07/2022

Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfer

While deep face recognition (FR) systems have shown amazing performance ...

0 Shengshan Hu, et al. ∙

∙ 01/19/2022

Defining Security Requirements with the Common Criteria: Applications, Adoptions, and Challenges

Advances of emerging Information and Communications Technology (ICT) tec...

0 Nan Sun, et al. ∙

∙ 12/29/2021

Challenges and approaches for mitigating byzantine attacks in federated learning

Recently emerged federated learning (FL) is an attractive distributed le...

0 Shengshan Hu, et al. ∙

∙ 05/23/2021

From Chaos to Pseudo-Randomness: A Case Study on the 2D Coupled Map Lattice

Applying chaos theory for secure digital communications is promising and...

0 Yong Wang, et al. ∙

∙ 05/19/2021

CREAMS: Copyrighted Cloud Media Sharing

The advent of the big data era drives the media data owner to seek help ...

0 Yushu Zhang, et al. ∙

∙ 05/08/2021

Self-Supervised Adversarial Example Detection by Disentangled Representation

Deep learning models are known to be vulnerable to adversarial examples ...

0 Zhaoxi Zhang, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world