Publications

* equal contribution † corresponding author. The full record is on Google Scholar.

2026

VEX-Bench: Benchmarking Verification Complexity of LLM-Generated Misinformation

Hanxun Huang, Yutao Wu, Qizhou Wang, Silvia Montaña-Niño, Yige Li, Xiang Zheng, Elif Buse Doyuran, Phoebe Matich,

NeurIPS 2026 E&D TrackarXiv OpenReview code project

Internal Safety Collapse in Frontier Large Language Models

Yutao Wu, Xiao Liu, Hanxun Huang, Yige Li, Xiang Zheng, Yifeng Gao, Cong Wang, Bo Li, Xingjun Ma, Yu-Gang Jiang

NeurIPS 2026arXiv code

HarmProfile: Characterizing Harmful Distributions in Frontier LLMs

Zhouyuan Ma, Yutao Wu, Hanxun Huang, Xiang Zheng, Xiao Liu, Yixin Cao, Zuxuan Wu, Xingjun Ma, Yu-Gang Jiang

EMNLP 2026 FindingsarXiv code

Practice Makes Unsafe: Skill Misevolution in Self-Improving LLM Agents

Xutao Mao, Liangjie Zhao, Xiang Zheng†, Cong Wang†

arXiv:2608.12851arXiv code

Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming

Xutao Mao, Xiang Zheng†, Cong Wang†

arXiv:2607.11698arXiv code

Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Stateful Personal Agents

Xutao Mao, Liangjie Zhao, Leyao Wang, Rui Qian, Qiang Huang, Wentao Wang, Bo Han, Xiang Zheng†, Cong Wang†

arXiv:2607.10526arXiv code

When Medical Safety Alignment Fails: A Benchmark for Evaluating LLMs on High-Risk Medical Queries

Yige Li, Jun Sun, Wei Zhao, Zhe Li, Yutao Wu, Hanxun Huang, Xiang Zheng, Xingjun Ma

arXiv:2606.28332arXiv

STARE: Step-wise Temporal Alignment and Red-teaming Engine for Multi-modal Toxicity Attack

Xutao Mao, Liangjie Zhao, Tao Liu, Xiang Zheng†, Hongying Zan, Cong Wang†

ICML 2026arXiv code

Just Ask: Curious Code Agents Reveal System Prompts in Frontier LLMs

Xiang Zheng, Yutao Wu, Hanxun Huang, Yige Li, Xingjun Ma†, Bo Li, Yu-Gang Jiang, Cong Wang†

ICML 2026arXiv code project

Defense-to-attack: Bypassing weak defenses enables stronger jailbreaks in Vision-Language Models

Yunhan Zhao, Xiang Zheng, Yige Li, Xingjun Ma†

Pattern Recognition (PR) 2026arXiv

Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses

Xiao Li*, Xiang Zheng*, Yifeng Gao, Xinyu Xia, Yixu Wang, Xin Wang, Ye Sun, Yunhan Zhao,

arXiv:2605.02900arXiv code project

Adapting Large Language Models for Encrypted Traffic Analysis Services: An Efficient Realization with Mixture of LoRA Experts

Yi Liu, Xiang Zheng, Chengjun Cai, Xingliang Yuan, Cong Wang†

IEEE Transactions on Services Computing (TSC) 2026

OpenRedRL: A Light-Weight Benchmark for Reinforcement Learning-Based Red Teaming

Xiang Zheng, Xingjun Ma, Wei-Bin Lee, Cong Wang†

Frontiers of Computer Science (FCS) 2026arXiv code

GenBreak: Red Teaming Text-to-Image Generation Using Large Language Models

Zilong Wang, Xiang Zheng†, Xiaosen Wang, Bo Wang, Xingjun Ma†

CVPR 2026arXiv code

OptiLeak: Efficient Prompt Reconstruction via Reinforcement Learning in Multi-tenant LLM Services

Longxiang Wang, Xiang Zheng†, Xuhao Zhang, Yao Zhang, Ye Wu, Cong Wang†

arXiv:2602.20595arXiv

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety

Xingjun Ma, Yifeng Gao, Yixu Wang, Ruofan Wang, Xin Wang, Ye Sun, Yifan Ding, Hengyuan Xu, Yunhao Chen, Yunhan Zhao, Hanxun Huang, Yige Li, Yutao Wu, Jiaming Zhang, Xiang Zheng,

Foundations and Trends in Privacy and Security (FnT P&S) 2026arXiv code

HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models

Zixing Chen, Yifeng Gao, Li Wang, Yunhan Zhao, Yi Liu, Jiayu Li, Xiang Zheng, Zuxuan Wu,

arXiv:2604.12447arXiv code

When Direct Prediction Fails: Evidence from LLM-Based Misinformation Risk Evaluation

Zonghuan Xu, Xiang Zheng, Yutao Wu, Xingjun Ma

arXiv:2604.06820arXiv

Constitutional On-Policy Safe Distillation

Ming Wen, Yuxuan Liu, Kun Yang, Yunhao Feng, Zhuoer Xu, Yuhao Sun, Shiwen Cui, Xiang Zheng,

arXiv:2606.03089arXiv project

DropVLA: An Action-Level Backdoor Attack on Vision-Language-Action Models

Zonghuan Xu, Jiayu Li, Yunhan Zhao, Xiang Zheng†, Xingjun Ma†, Yu-Gang Jiang

IROS 2026arXiv code

2025

AttackVLA: Benchmarking Adversarial and Backdoor Attacks on Vision-Language-Action Models

Jiayu Li, Yunhan Zhao, Xiang Zheng, Zonghuan Xu, Yige Li, Xingjun Ma, Yu-Gang Jiang

arXiv:2511.12149arXiv code

ADMIT: Few-shot Knowledge Poisoning Attacks on RAG-based Fact Checking

Yutao Wu, Xiao Liu, Yinghui Li, Yifeng Gao, Yifan Ding, Jiale Ding, Xiang Zheng, Xingjun Ma

arXiv:2510.13842arXiv

RedTopic: Toward Topic-Diverse Red Teaming of Large Language Models

Jiale Ding, Xiang Zheng†, Yutao Wu, Cong Wang, Wei-Bin Lee, Ling Pan, Xingjun Ma†, Yu-Gang Jiang

arXiv:2507.00026arXiv

BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks

Yunhan Zhao, Xiang Zheng†, Lin Luo, Yige Li, Xingjun Ma†, Yu-Gang Jiang

ICLR 2025arXiv code

CALM: Curiosity-Driven Auditing for Large Language Models

Xiang Zheng, Longxiang Wang, Yi Liu, Xingjun Ma, Chao Shen, Cong Wang†

AAAI 2025arXiv code

2024

Constrained intrinsic motivation for reinforcement learning

Xiang Zheng, Xingjun Ma, Chao Shen, Cong Wang†

IJCAI 2024arXiv code

Toward evaluating robustness of reinforcement learning with adversarial policy

Xiang Zheng, Xingjun Ma, Shengjie Wang, Xinyu Wang, Chao Shen, Cong Wang†

DSN 2024arXiv code

2023

A policy optimization method towards optimal-time stability

Shengjie Wang, Fengbo Lan, Xiang Zheng, Yuxue Cao, Oluwatosin Oseni, Haotian Xu, Tao Zhang, Yang Gao

CoRL 2023arXiv project

A Learning-based Adaptive Compliance Method for Symmetric Bi-manual Manipulation

Yuxue Cao, Wenhao Zhao, Shengjie Wang, Xiang Zheng, Wenke Ma, Ziwei Wang, Tao Zhang

arXiv:2303.15262arXiv project

Reinforcement learning with prior policy guidance for motion planning of dual-arm free-floating space robot

Yuxue Cao, Shengjie Wang, Xiang Zheng, Wenke Ma, Xinru Xie, Lei Liu

Aerospace Science and Technology (AST) 2023

2022

A learning system for motion planning of free-float dual-arm space manipulator towards non-cooperative object

Shengjie Wang, Yuxue Cao, Xiang Zheng, Tao Zhang

Aerospace Science and Technology (AST) 2022

Collision-free trajectory planning for a 6-DoF free-floating space robot via hierarchical decoupling optimization

Shengjie Wang, Yuxue Cao, Xiang Zheng, Tao Zhang

IEEE Robotics and Automation Letters (RA-L) 2022

2021

A multi-target trajectory planning of a 6-DoF free-floating space robot via reinforcement learning

Shengjie Wang, Xiang Zheng, Yuxue Cao, Tao Zhang

IROS 2021

An end-to-end trajectory planning strategy for free-floating space robots

Shengjie Wang, Yuxue Cao, Xiang Zheng, Tao Zhang

CCC 2021

2020

Clean-label backdoor attacks on video recognition models

Shihao Zhao, Xingjun Ma, Xiang Zheng, James Bailey, Jingjing Chen, Yu-Gang Jiang

CVPR 2020

2017

Robust finite-time attitude tracking control for nonlinear quadrotor with uncertainties and delays

Xiang Zheng, Ziwei Wang, Tao Zhang

ROBIO 2017