Xiaogeng Liu
12 papers · 2022–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Cross-Pollinator (5) π Conference Polyglot (6) π Interdisciplinary Bridge π§ Keyword Pioneer π Renaissance Researcher (6)
πΊοΈ
Taxonomy Completionist
(16)
π
Interdisciplinary Bridge
π€
Dynamic Duo
(11)
π₯
Mega-Team
(21)
β
The Questioner
β‘
Prolific Year
(8)
π
Century Club
(12)
Conferences
ICLR (4)
ACL (2)
CVPR (2)
NAACL (2)
ECCV (1)
ICML (1)
Top co-authors
Research topics
Keywords
adversarial learning
(2)
large language model
(2)
risk management
(1)
neural network security
(1)
text classification
(1)
face recognition
(1)
corruption robustness
(1)
adversarial detection
(1)
autonomous agent
(1)
generative adversarial network
(1)
adversarial example
(1)
jailbreak attack
(1)
privacy protection
(1)
makeup transfer
(1)
prompt injection
(1)
agent system
(1)
software security
(1)
llm agent
(1)
llm safety
(1)
retrieval-based method
(1)
Papers
RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process
NAACL 2025
PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free
ACL 2025
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
ICLR 2025
MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines
ICML 2025
CVE-Bench: Benchmarking LLM-based Software Engineering Agentβs Ability to Repair Real-World CVE Vulnerabilities
NAACL 2025
AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection
ACL 2025
Can Watermarks be Used to Detect LLM IP Infringement For Free?
ICLR 2025
AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
ICLR 2025
AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting
ECCV 2024
AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
ICLR 2024
Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency
CVPR 2023
Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-Robust Makeup Transfer
CVPR 2022