Scholar
Ruihan Wu
Google Scholar ID: DsHKK-AAAAAJ
University of California, San Diego
machine learning
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
548
H-index
13
i10-index
15
Publications
20
Co-authors
0
Contact
CV
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
12 items
One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue
2026
Cited
0
DPrivBench: Benchmarking LLMs' Reasoning for Differential Privacy
2026
Cited
0
A Wolf in Sheep's Clothing: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search
2025
Cited
0
Private-RAG: Answering Multiple Queries with LLMs while Keeping Your Data Private
2025
Cited
0
Learning-Time Encoding Shapes Unlearning in LLMs
2025
Cited
0
Can We Infer Confidential Properties of Training Data from LLMs?
2025
Cited
0
Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
2025
Cited
0
New Rates in Stochastic Decision-Theoretic Online Learning under Differential Privacy
2025
Cited
0
Load more
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up