collaborators

10 papers

cs.AI2026

SHE: Trajectory-driven Safety Harness Evolution for LLM Agents

Wanying Qu, Qinghua Mao, Yu Li +12

The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that manages context, memory, tools, permissions, and runtime contro…

cs.CR2026

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

Siyuan Li, Aodu Wulianghai, Zehao Liu +8

Large Language Models (LLMs) are increasingly deployed in interactive settings, where user intent commonly unfolds through multi-turn dialogue. Multi-turn jailbreaks exploit this p…

cs.AI2026

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

Dongrui Liu, Yu Li, Zhonghao Yang +47

Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI mod…

cs.CR2026

GraphSteal: Structural Knowledge Stealing from Graph RAG via Traversal Reconstruction

Jinze Gu, Qinghua Mao, Xi Lin +1

Retrieval-Augmented Generation (RAG) enhances LLMs by grounding generation in query-relevant external evidence. Beyond unstructured text corpora, Graph RAG integrates knowledge gra…

cs.CR2026

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

Leitao Yuan, Qinghua Mao, Daizong Liu +5

Multimodal large language models (MLLMs) remain vulnerable to transfer-based targeted attacks, where perturbations optimized on open-source surrogate encoders can generalize to clo…

cs.AI2026

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

Qinghua Mao, Xi Lin, Jinze Gu +3

Large language models (LLMs) increasingly rely on knowledge editing to support knowledge-intensive reasoning, but this flexibility also introduces critical safety risks: adversarie…