Zixuan Zhu
4 papers · 2023–2026 · 4 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 · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
Top co-authors
Research topics
Artificial Intelligence
(4)
Core AI
(4)
Machine Learning
(2)
Learning Types · Machine Learning
(2)
Deep Learning
(1)
Natural Language Processing
(1)
Security & Privacy
(1)
Application Areas
(1)
Applications
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory
(1)
Privacy
(1)
Resources & Methods
(1)
Techniques
(1)
Keywords
semi-supervised learning
(1)
data augmentation
(1)
in-context learning
(1)
false positive
(1)
backdoor attack
(1)
semantic understanding
(1)
gradient matching
(1)
adversarial patch
(1)
entropy-based method
(1)
poisoned model
(1)
neural network
(1)
multi-document question answering
(1)
backdoor watermark
(1)
reasoning mechanism
(1)
entropy constraint
(1)
dataset copyright protection
(1)
clean-label watermarking
(1)
patch localization
(1)
knowledge graph prompting
(1)
dataset copyright
(1)
Papers
False Positives Matter: Multidimensional Localization Evaluation and Training-Free Explainable Adversarial Patch Defense
AAAI 2026
CuriousLLM: Elevating Multi-Document Question Answering with LLM-Enhanced Knowledge Graph Reasoning
NAACL 2025
EntropyMark: Towards More Harmless Backdoor Watermark via Entropy-based Constraint for Open-source Dataset Copyright Protection
CVPR 2025
The Victim and The Beneficiary: Exploiting a Poisoned Model to Train a Clean Model on Poisoned Data
ICCV 2023