Ganghua Wang
7 papers · 2023–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(4)
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(15)
👑
Triple Crown
Conferences
ICLR (2)
ICML (2)
NIPS (2)
EMNLP (1)
Top co-authors
Keywords
learning theory
(1)
adversarial robustness
(1)
model security
(1)
deep learning
(1)
false positive rate
(1)
domain knowledge
(1)
backdoor attack
(1)
adversarial attack
(1)
generative model
(1)
latent representation
(1)
poisoning attack
(1)
feature engineering
(1)
watermark detection
(1)
tabular prediction
(1)
kernel-based learning
(1)
backdoor detection
(1)
kernel methods
(1)
large language model
(1)
neural network
(1)
automated data science
(1)
Papers
AssistedDS: Benchmarking How External Domain Knowledge Assists LLMs in Automated Data Science
EMNLP 2025
On the Vulnerability of Applying Retrieval-Augmented Generation within Knowledge-Intensive Application Domains
ICML 2025
Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
ICLR 2024
RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
NIPS 2024
Pruning Deep Neural Networks from a Sparsity Perspective
ICLR 2023
A Unified Detection Framework for Inference-Stage Backdoor Defenses
NIPS 2023
Understanding Backdoor Attacks through the Adaptability Hypothesis
ICML 2023