Wenshu Fan
4 papers · 2025–2026 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(2)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
Conferences
AAAI (3)
ICML (1)
Top co-authors
Keywords
adversarial learning
(1)
model security
(1)
autoregressive generation
(1)
conditional generation
(1)
machine unlearning
(1)
backdoor attack
(1)
tool selection
(1)
genetic algorithm
(1)
prompt injection
(1)
sliding window
(1)
backdoor detection
(1)
real-time detection
(1)
large language model
(1)
model context protocol
(1)
preference manipulation
(1)
token confidence
(1)
sequence lock
(1)
attack stealthiness
(1)
Papers
ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models
AAAI 2026
MPMA: Preference Manipulation Attack Against Model Context Protocol
AAAI 2026
Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models
AAAI 2025
Omni-Angle Assault: An Invisible and Powerful Physical Adversarial Attack on Face Recognition
ICML 2025