◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Kun He

4 papers hereh-index 224 citations10 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • middle author1
  • last author2

Across the 3 of 4 papers where every author was matched, so the position is known.

fields
  • cs.CV2
  • cs.CL1
  • cs.LG1
same name
  • Kun He — 17 papers, h 22
  • Kun He — 14 papers, h 26
  • Kun He — 11 papers
  • Kun He — 11 papers, h 10
  • Kun He — 11 papers, h 19
  • Kun He — 6 papers, h 5

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

activity
20232025
most citedRevisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack

1 citations · 1 across the 3 of their papers we have counts for

collaborators

4 papers

cs.CV2025

Enhancing Adversarial Transferability in Visual-Language Pre-training Models via Local Shuffle and Sample-based Attack

Xin Liu, Aoyang Zhou

Visual-Language Pre-training (VLP) models have achieved significant performance across various downstream tasks. However, they remain vulnerable to adversarial examples. While prio…

cs.LG2024★ 1 cited

Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack

Xin Liu, Yuxiang Zhang, Meng Wu +6

Edge perturbation is a basic method to modify graph structures. It can be categorized into two veins based on their effects on the performance of graph neural networks (GNNs), i.e.…

cs.CL2024

Fast Adversarial Training against Textual Adversarial Attacks

Yichen Yang, Xin Liu, Kun He

Many adversarial defense methods have been proposed to enhance the adversarial robustness of natural language processing models. However, most of them introduce additional pre-set…

cs.CV2023

AutoAugment Input Transformation for Highly Transferable Targeted Attacks

Haobo Lu, Xin Liu, Kun He

Deep Neural Networks (DNNs) are widely acknowledged to be susceptible to adversarial examples, wherein imperceptible perturbations are added to clean examples through diverse input…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.