Research

Problems I keep returning to

My research focuses on Trustworthy AI, Human-Centered AI, and DeFi & Blockchain, with a recent emphasis on safety and privacy for embodied AI systems.

01 9 papers Trustworthy AI

Jailbreak robustness, AI-powered search safety, privacy risk, covert content, and reliable evaluation for frontier AI systems.

03 4 papers DeFi & Blockchain

Secure and efficient decentralized protocols, smart contract analysis, gas optimization, payment channels, and cross-chain financial primitives.

* denotes equal contribution. A full list is also available on Google Scholar.

Topic 01 · 9 papers

Trustworthy AI

Jailbreak robustness, AI-powered search safety, privacy risk, covert content, and reliable evaluation for frontier AI systems.

2026

arXiv 2026

What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Media

Zifan Peng, Yini Huang, Aiwen Lu, Qiming Ye, Peixian Zhang, Jingyi Zheng, Yule Liu, Xuechao Wang, Xinlei He, Jiaheng Wei

arXiv preprint arXiv:2606.06784

DOI

2026

arXiv 2026

Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network

Qiming Ye, Peixain Zhang, Yupeng He, Zifan Peng, Gareth Tyson

arXiv preprint arXiv:2605.25815

DOI

2026

arXiv 2026

On the Generation and Mitigation of Harmful Geometry in Image-to-3D Models

Yule Liu, Yilong Yang, Jiale Teng, Hanze Jia, Zeren Luo, Jingyi Zheng, Zifan Peng, Ke Li, Yifan Liao, Zhen Sun, Jiaheng Wei, Yang Liu, Zhuo Ma, Xinlei He

arXiv preprint arXiv:2605.09606

DOI

2026

ICLR 2026

JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models

Zifan Peng, Yule Liu, Zhen Sun, Mingchen Li, Zeren Luo, Jingyi Zheng, Wenhan Dong, Xinlei He, Xuechao Wang, Yingjie Xue, Shengmin Xu, Xinyi Huang

International Conference on Learning Representations

DOI

2025

arXiv 2025

Source Coverage and Citation Bias in LLM-based vs. Traditional Search Engines

Peixian Zhang*, Qiming Ye*, Zifan Peng, Kiran Garimella, Gareth Tyson

arXiv preprint arXiv:2512.09483

DOI

2025

arXiv 2025

GRPO Privacy Is at Risk: A Membership Inference Attack Against Reinforcement Learning With Verifiable Rewards

Yule Liu, Heyi Zhang, Jinyi Zheng, Zhen Sun, Zifan Peng, Tianshuo Cong, Yilong Yang, Xinlei He, Zhuo Ma

arXiv preprint arXiv:2511.14045

DOI

2025

NeurIPS 2025

CHASM: Unveiling Covert Advertisements on Chinese Social Media

Jingyi Zheng*, Tianyi Hu*, Yule Liu, Zhen Sun, Zongmin Zhang, Wenhan Dong, Zifan Peng, Xinlei He

Conference on Neural Information Processing Systems

DOI

2025

USENIX Security 2025

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search

Zeren Luo*, Zifan Peng*, Yule Liu, Zhen Sun, Mingchen Li, Jingyi Zheng, Xinlei He

USENIX Security Symposium

DOI

2025

arXiv 2025

Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models

Yule Liu, Jingyi Zheng, Zhen Sun, Zifan Peng, Wenhan Dong, Zeyang Sha, Shiwen Cui, Weiqiang Wang, Xinlei He

arXiv preprint arXiv:2504.13626

DOI

Topic 02 · 10 papers

Human-Centered AI

LLM evaluation, policy simulation, cognitive assessment, visual assistance, human-agent applications, and applied machine learning.

2026

arXiv 2026

"What Did It Actually Do?": Understanding Risk Awareness and Traceability for Computer-Use Agents

Zifan Peng, Mingchen Li

arXiv preprint arXiv:2603.28551

DOI

2026

JASSS 2026

GPLab: A Generative Agent-Based Framework for Policy Simulation and Evaluation

Shuhan Zhang, Zifan Peng, Yinwang Ren

Journal of Artificial Societies & Social Simulation, 29(1), 1

DOI PDF

2026

ICML 2026

NL2Repo-Bench: Towards Long-Horizon Repository Generation Evaluation of Coding Agents

Zifan Peng, etc.

International Conference on Machine Learning

ICML DOI

2025

NeurIPS 2025

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Zifan Peng, etc.

Conference on Neural Information Processing Systems

DOI

2025

arXiv 2025

ZPD-SCA: Unveiling the Blind Spots of LLMs in Assessing Students' Cognitive Abilities

Wenhan Dong, Zhen Sun, Yuemeng Zhao, Zifan Peng, Jun Wu, Jingyi Zheng, Yule Liu, Xinlei He, Yu Wang, Ruiming Wang, Xinyi Huang, Lei Mo

arXiv preprint arXiv:2508.14377

DOI

2025

arXiv 2025

"I Can See Forever!": Evaluating Real-time VideoLLMs for Assisting Individuals with Visual Impairments

Ziyi Zhang*, Zhen Sun*, Zongmin Zhang, Zifan Peng, Yuemeng Zhao, Zichun Wang, Zeren Luo, Ruiting Zuo, Xinlei He

arXiv preprint arXiv:2505.04488

DOI

2025

arXiv 2025

Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications

Wenhan Dong*, Yuemeng Zhao*, Zhen Sun, Yule Liu, Zifan Peng, Jingyi Zheng, Zongmin Zhang, Ziyi Zhang, Jun Wu, Ruiming Wang, Shengmin Xu, Xinyi Huang, Xinlei He

arXiv preprint arXiv:2505.00049

DOI

2025

arXiv 2025

Automatic Pruning via Structured Lasso with Class-wise Information

Xiang Liu*, Mingchen Li*, Xia Li, Leigang Qu, Zifan Peng, Yijun Song, Zemin Liu, Linshan Jiang, Jialin Li

arXiv preprint arXiv:2502.09125

DOI

2025

MLJ 2025

Prompt-based Contrastive Learning to Combat the COVID-19 Infodemic

Zifan Peng, Mingchen Li, Yue Wang, George T.S. Ho

Machine Learning, 114(1), 6

DOI

2024

ESWA 2024

Combating the COVID-19 Infodemic Using Prompt-Based Curriculum Learning

Zifan Peng, Mingchen Li, Yue Wang, George T.S. Ho

Expert Systems with Applications, 229, 120501

DOI

Topic 03 · 4 papers

DeFi & Blockchain

Secure and efficient decentralized protocols, smart contract analysis, gas optimization, payment channels, and cross-chain financial primitives.

2026

arXiv 2026

TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding

Zifan Peng, Jingyi Zheng, Yule Liu, Huaiyu Jia, Qiming Ye, Jingyu Liu, Xufeng Yang, Mingchen Li, Qingyuan Gong, Xuechao Wang, Xinlei He

arXiv preprint arXiv:2512.06933

DOI

2025

arXiv 2025

GasAgent: A Multi-Agent Framework for Automated Gas Optimization in Smart Contracts

Jingyi Zheng*, Zifan Peng*, Yule Liu, Junfeng Wang, Yifan Liao, Wenhan Dong, Xinlei He

arXiv preprint arXiv:2507.15761

DOI

2025

ICWS 2025

Cross-Chain Options: A Bridgeless, Universal, and Efficient Approach

Zifan Peng, Yingjie Xue, Jingyu Liu

IEEE International Conference on Web Services

DOI

2025

TDSC 2025

FairRelay: Fair and Cost-Efficient Peer-to-Peer Content Delivery through Payment Channel Networks

Jingyu Liu, Yingjie Xue, Zifan Peng, Chao Lin, Xinyi Huang

IEEE Transactions on Dependable and Secure Computing

DOI