◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Wei Wan

14 papers hereh-index 12452 citations32 works total

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

author position
  • first author1
  • middle author13

Across the 14 of 14 papers where every author was matched, so the position is known.

fields
  • cs.CV5
  • cs.CR3
  • cs.LG3
  • cs.AI1
  • cs.CL1
  • cs.DC1
same name
  • Wei Wan — 2 papers, h 5
  • Wei Wan — 2 papers
  • Wei Wan — 2 papers, h 1
  • Wei Wan — 1 paper, h 8
  • Wei Wan — 1 paper
  • Wei Wan — 1 paper

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
20212025
most citedDarkFed: A Data-Free Backdoor Attack in Federated Learning

1 citations · 1 across the 12 of their papers we have counts for

collaborators
Showing cs.CRShow all

4 papers · 1 filter

cs.CR2026

Defending Jailbreak Attacks on Large Language Models via Manifold Trajectory Kinetics

Hangtao Zhang, Yucheng Zhao, Sishun Liu +8

Jailbreak prompts can bypass alignment guardrails in large language models (LLMs) and elicit unsafe outputs, making reliable deployment-time detection critical. Prior detection app…

cs.CR2025

MARS: A Malignity-Aware Backdoor Defense in Federated Learning

Wei Wan, Yuxuan Ning, Zhicong Huang +7

Federated Learning (FL) is a distributed paradigm aimed at protecting participant data privacy by exchanging model parameters to achieve high-quality model training. However, this…

cs.CR2025

Spa-VLM: Stealthy Poisoning Attacks on RAG-based VLM

Lei Yu, Yechao Zhang, Ziqi Zhou +6

With the rapid development of the Vision-Language Model (VLM), significant progress has been made in Visual Question Answering (VQA) tasks. However, existing VLM often generate ina…

cs.CR2024★ 1 cited

DarkFed: A Data-Free Backdoor Attack in Federated Learning

Minghui Li, Wei Wan, Yuxuan Ning +4

Federated learning (FL) has been demonstrated to be susceptible to backdoor attacks. However, existing academic studies on FL backdoor attacks rely on a high proportion of real cli…

◍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.