◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Xiaogeng Liu

32 papers hereh-index 192.5k citations43 works total

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

author position
  • first author8
  • middle author22

Across the 30 of 32 papers where every author was matched, so the position is known.

fields
  • cs.CR19
  • cs.AI4
  • cs.LG4
  • cs.CV3
  • cs.CL2
same name
  • Xiaogeng Liu — 1 paper, h 3

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
20222026
most citedAutomatic and Universal Prompt Injection Attacks against Large Language Models

10 citations · 25 across the 26 of their papers we have counts for

collaborators
Showing cs.CLShow all

2 papers · 1 filter

cs.CL2024★ 2 cited

InjecGuard: Benchmarking and Mitigating Over-defense in Prompt Injection Guardrail Models

Hao Li, Xiaogeng Liu

Prompt injection attacks pose a critical threat to large language models (LLMs), enabling goal hijacking and data leakage. Prompt guard models, though effective in defense, suffer…

cs.CL2023

AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Xiaogeng Liu, Nan Xu, Muhao Chen +1

The aligned Large Language Models (LLMs) are powerful language understanding and decision-making tools that are created through extensive alignment with human feedback. However, th…

◍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.