Wenbo Jiang
8 papers · 2023–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
π Conference Polyglot (4) π Renaissance Researcher (6) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (15) π§ Keyword Pioneer
π
Cross-Pollinator
(15)
Conferences
AAAI (4)
ICML (2)
CVPR (1)
EMNLP (1)
Top co-authors
Research topics
Keywords
backdoor attack
(2)
model security
(1)
adversarial machine learning
(1)
cross-lingual transfer
(1)
autoregressive generation
(1)
multimodal learning
(1)
conditional generation
(1)
instruction following
(1)
machine unlearning
(1)
model adaptation
(1)
adversarial attack
(1)
attention head
(1)
tool selection
(1)
robustness evaluation
(1)
multimodal model
(1)
genetic algorithm
(1)
prompt injection
(1)
sliding window
(1)
backdoor detection
(1)
particle swarm optimization
(1)
Papers
MPMA: Preference Manipulation Attack Against Model Context Protocol
AAAI 2026
Focusing on Language: Revealing and Exploiting Language Attention Heads in Multilingual Large Language Models
AAAI 2026
ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models
AAAI 2026
Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models
AAAI 2025
The Ripple Effect: On Unforeseen Complications of Backdoor Attacks
ICML 2025
Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study
EMNLP 2025
Omni-Angle Assault: An Invisible and Powerful Physical Adversarial Attack on Face Recognition
ICML 2025
Color Backdoor: A Robust Poisoning Attack in Color Space
CVPR 2023