Author

Qinghua Mao

Observed name: Mao, Qinghua

Institutions: Nanyang Technological University, Shanghai Jiao Tong University, Shanghai Artificial Intelligence Laboratory

Observed institutions: Nanyang Technological University, Shanghai Jiao Tong University, Shanghai Artificial Intelligence Laboratory

OpenAlex ID: A5137334851

Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs

2026 · Yuan, Leitao, Mao, Qinghua, et al. · arXiv (Cornell University) · 1

Before Agent Tells The Lie: Has Deception Already Been Represented?

2026 · Li, Xinling, Guo, Dadi, et al. · arXiv (Cornell University)

SafeEvolve: Harness-Policy Co-Evolution from Agent Experience for Safety Alignment

2026 · Mao, Qinghua, Qu, Wanying, et al. · arXiv (Cornell University)

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents

2026 · Qu, Wanying, Mao, Qinghua, et al. · arXiv (Cornell University)

SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks

2026 · Li, Siyuan, Wulianghai, Aodu, et al. · arXiv (Cornell University)

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

2026 · Liu, Dongrui, Li, Yu, et al. · arXiv (Cornell University)

GraphSteal: Structural Knowledge Stealing from Graph RAG via Traversal Reconstruction

2026 · Gu, Jinze, Mao, Qinghua, et al. · arXiv (Cornell University)

Benchmarking Safety Risks of Knowledge-Intensive Reasoning under Malicious Knowledge Editing

2026 · Mao, Qinghua, Lin, Xi, et al. · arXiv (Cornell University)

Lightweight Stylistic Consistency Profiling: Robust Detection of LLM-Generated Textual Content for Multimedia Moderation

2026 · Li, Siyuan, Wulianghai, Aodu, et al. · arXiv (Cornell University)

DSIPA: Detecting LLM-Generated Texts via Sentiment-Invariant Patterns Divergence Analysis

2026 · Li, Siyuan, Wulianghai, Aodu, et al. · arXiv (Cornell University)

CoopGuard: Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Round Attacks

2026 · Li, Siyuan, Liu, Zehao, et al. · arXiv (Cornell University)

Is There a Structural Privacy Risk in Graph Prompting with LLMs?

2026 · Jiani Zhu, Xi Lin, et al. · Lecture notes in computer science

Search Engine Augmented Chinese Named Entity Recognition for Big Data Content Security

2025 · Qinghua Mao, Jiatong Li, et al.

Works count: 13

Citation count: 1

H-index: 1

I10-index: