Scholar

Zhanhao Hu

Google Scholar ID: PGdm9MUAAAAJ

University of California, Berkeley

large language modelsadversarial examplesprivacysecurity

Homepage↗Google Scholar↗

Citations & Impact

All-time

Citations

431

H-index

9

i10-index

9

Publications

19

Co-authors

0

Contact

No contact links provided.

Publications

7 items

GradShield: Alignment Preserving Finetuning

2026

Cited

0

Physical Adversarial Clothing Evades Visible-Thermal Detectors via Non-Overlapping RGB-T Pattern

2026

Cited

0

A Single Set of Adversarial Clothes Breaks Multiple Defense Methods in the Physical World

2025

Cited

0

Better Privilege Separation for Agents by Restricting Data Types

2025

Cited

0

JULI: Jailbreak Large Language Models by Self-Introspection

2025

Cited

0

JailbreaksOverTime: Detecting Jailbreak Attacks Under Distribution Shift

2025

Cited

0

PromptShield: Deployable Detection for Prompt Injection Attacks

2025

Cited

0

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)