AI safety researcher

Hongxin Hu

Google Scholar dblp ORCID

Last 12 months7 papers

AI safety papers from the last year

On this site: 20 papers

September 2026

NetInspector: Measuring and Improving LLM Capabilities for Reliable Intent-Based Networking Policy Generation
Sep 17arXiv ↗

August 2026

Breaking Planner Integrity Boundary: Enviroment State-Text Injection Attack on LLM-Driven Embodied Agents
Aug 17arXiv ↗
MMAligner: Safeguarding Multimodal Large Language Models through Representation Calibration
Aug 6arXiv ↗

June 2026

February 2026

AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
Feb 26arXiv ↗

November 2025

DualGauge: Automated Joint Security-Functionality Benchmarking of Specification-Only Code Generation by LLMs and Coding Agents
Nov 24arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.