Scholar

Will Cai

Google Scholar ID: rP3Ed1oAAAAJ

UC Berkeley

AI SafetyAI Security

Google Scholar↗

Citations & Impact

All-time

Citations

248

H-index

5

i10-index

2

Publications

5

Co-authors

0

Contact

No contact links provided.

Publications

5 items

The Geometry of Harmfulness in LLMs through Subconcept Probing

2025

Cited

0

PromptArmor: Simple yet Effective Prompt Injection Defenses

2025

Cited

0

Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs

2025

Cited

0

Improving LLM Safety Alignment with Dual-Objective Optimization

2025

Cited

0

Data Poisoning in LLMs: Jailbreak-Tuning and Scaling Laws

2024

Cited

6

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)