Xiaogeng Liu
12 papers · 2022–2025 · 6 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (22) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🤝 Dynamic Duo (11)
👥
Mega-Team · Squad
⚡
Prolific Year · Productive
❓
The Questioner
💎
Century Club · Bronze
🗃️
Keyword Collector
(59)
Top co-authors
Research topics
Artificial Intelligence
(11)
Core AI
(11)
Machine Learning
(6)
Deep Learning
(3)
Application Areas
(3)
Learning Types · Machine Learning
(3)
Computer Vision
(2)
Natural Language Processing
(2)
Analysis
(2)
Learning Types · Deep Learning
(2)
Resources & Methods
(2)
Security & Privacy
(1)
Models
(1)
Optimization & Theory
(1)
Privacy
(1)
Keywords
large language model
(5)
jailbreak attack
(3)
agent system
(2)
adversarial learning
(2)
state transition
(1)
face recognition
(1)
text classification
(1)
model alignment
(1)
neural network security
(1)
optimization algorithm
(1)
corruption robustness
(1)
language model
(1)
adversarial detection
(1)
autonomous agent
(1)
watermark detection
(1)
generative adversarial network
(1)
adversarial example
(1)
intellectual property
(1)
privacy protection
(1)
risk management
(1)
Papers
AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection
ACL 2025
AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
ICLR 2025
Can Watermarks be Used to Detect LLM IP Infringement For Free?
ICLR 2025
CVE-Bench: Benchmarking LLM-based Software Engineering Agent’s Ability to Repair Real-World CVE Vulnerabilities
NAACL 2025
MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines
ICML 2025
MuirBench: A Comprehensive Benchmark for Robust Multi-image Understanding
ICLR 2025
PIGuard: Prompt Injection Guardrail via Mitigating Overdefense for Free
ACL 2025
RePD: Defending Jailbreak Attack through a Retrieval-based Prompt Decomposition Process
NAACL 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