Scholar

Linghan Huang

Google Scholar ID: 9b_rfZUAAAAJ

The University of Sydney

Trustworthy MLSoftware Security

Homepage↗Google Scholar↗

Citations & Impact

All-time

Citations

194

H-index

4

i10-index

3

Publications

9

Co-authors

0

Contact

TwitterOpen ↗

Publications

7 items

Trust in One Round: Confidence Estimation for Large Language Models via Structural Signals

2026

Cited

0

Feature-Selective Representation Misdirection for Machine Unlearning

2025

Cited

0

LLMs are All You Need? Improving Fuzz Testing for MOJO with Large Language Models

2025

Cited

0

The Tower of Babel Revisited: Multilingual Jailbreak Prompts on Closed-Source Large Language Models

2025

Cited

0

From Compliance to Exploitation: Jailbreak Prompt Attacks on Multimodal LLMs

2025

Cited

0

From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future

arXiv.org · 2024

Cited

17

On the Challenges of Fuzzing Techniques via Large Language Models

2024

Cited

14

Resume (English only)

Co-authors

0 total

Co-authors: 0 (list not available)