Yuepeng Hu
6 papers · 2024–2026 · 5 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 ↓
🌍
Conference Polyglot · Silver
Top co-authors
Research topics
Keywords
adversarial perturbation
(3)
multimodal large language model
(2)
prompt injection
(2)
adversarial attack
(1)
text-to-image model
(1)
evasion attack
(1)
watermark detection
(1)
jailbreak attack
(1)
adversarial prompt
(1)
transfer attack
(1)
statistical guarantee
(1)
web agent
(1)
safety guardrail
(1)
large language model
(1)
image protection
(1)
image watermark
(1)
visual prompt injection
(1)
refusal response
(1)
model fingerprinting
(1)
provenance detection
(1)
Papers
Fingerprinting LLMs via Prompt Injection
ACL 2026
Jailbreaking Safeguarded Text-to-Image Models via Large Language Models
EACL 2026
Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection
ACL 2026
A Transfer Attack to Image Watermarks
ICLR 2025
WebInject: Prompt Injection Attack to Web Agents
EMNLP 2025
Certifiably Robust Image Watermark
ECCV 2024