About Me

Hello! I am Zhihua Wang, an incoming CS master's student at Fudan University's Vision and Learning Laboratory (FVL), led by Prof. Yu-Gang Jiang (Vice President, Fudan University), and the Institute of Trustworthy Embodied Artificial Intelligence (TEAI). I will be advised by Prof. Xingjun Ma. I am pursuing a bachelor's degree in Computer Science and Technology at the School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology (USST) (2023–2027). My open-source projects have received approximately 2.5k GitHub Stars, and I won an ACM silver medal.

I am currently an LLM research intern at the Third Research Institute of the Ministry of Public Security (TRIMPS), guided by Nan Li, working on Web Agent and LLM safety evaluation benchmarks. I also collaborate with Yutao Wu, a PhD student at Deakin University, and Yunhao Feng, a PhD student interning at (Ant Group), on multi-agent systems, coding agents, and trustworthy AI.

My research interests include foundation models, coding agents, agent post-training and reinforcement learning, and trustworthy AI. 🙂(:

News

MemHarmBench was recommended by Shanghai Innovation Institute and featured in MiraclePlus's Alpha Sight.

Alpha Sight recommendation

Alpha Sight's 2026.11.04 digest recommending MemHarmBench, highlighted in the original screenshot.
Open original image in a new window

Participated in the open-source projects AISafetyHot and prompt-spider-ui during China's National Day holiday. Many thanks to my collaborators for their support and ideas.

Joined Advisor Jingfeng Zhang's RISE-AI Lab as a visiting student at TEAI, Fudan University and began research on MemHarmBench, a benchmark for persistent-memory poisoning in agents. The work adopts a victim-centered perspective to design evaluation cases and examines who ultimately bears the loss after an agent is compromised.

Began serving as a reviewer for NeurIPS 2026, contributing to the peer-review process for research in machine learning and artificial intelligence.

At TEAI, Fudan University, under the guidance of Advisor Xingjun Ma, I participated in an enterprise-oriented multi-agent secure collaboration project, contributing to requirements analysis, system design, implementation, and testing.

Completed an International Organization Internship through the UNDP-administered UNV platform on mangrove responses to climate change and produced a review manuscript on blue carbon mitigation.

Started SafeCodeRL, a multi-agent reinforcement learning framework for safety-constrained LLM code generation.

My chapter as an ACMer officially came to an end.

Preprints and Publications

ScamWeb dataset overview showing data sources, webpage collection and recovery, processed multimodal artifacts, expert annotations, dataset composition, and representative samples. AAAI 2027 · CCF A

ScamWeb: A Multimodal Benchmark for Grounded Understanding of Cyber-enabled Fraud Webpages

Zhihua Wang*, Nan Li*, Ziyang Chen, Yunhao Feng, Songyang Wu†

* Co-first author (equal contribution) · † Corresponding author

Co-first author · AAAI 2027; Will be accepted(accept*4)

Multimodal BenchmarkCyber-enabled FraudGrounded UnderstandingEvidence LocalizationLLM-VLMTrustworthy AI
MemHarmBench Figure 1: an instruction from an external note is retained in memory; after the note is removed, a new session completes the expense summary but changes its recipient to the attacker's choice. Preprint

MemHarmBench: Evaluating Cross-Session Prompt Injection in Memory-Persistent AI Agents

Zhihua Wang, Yunhao Feng, Yifeng Gao, Rui Pan, Baiheng Zhao, Zixing Chen, Xingjun Ma†

† Corresponding author

First author · arXiv preprint

LLM AgentsPersistent MemoryCross-Session Prompt InjectionVictim-Centric EvaluationAgent SafetyBenchmark
Original CST framework diagram: source-local context, lightweight feature fusion and topic discovery, risk triage, and source-grounded evidence for review. Preprint

CST: Lightweight Risk Triage with Source-Grounded Evidence for Web Discussions

Zhihua Wang, Yifeng Gao†, Yunhao Feng, Rui Pan, Baiheng Zhao, Zixing Chen, Nan Li

† Corresponding author

First author · arXiv preprint

Risk TriageSource-Grounded EvidenceWeb DiscussionsMultilingual NLPCPU Inference
SafeCodeRL framework diagram showing IoT/CPS contexts, a five-agent closed loop, constraint-aware optimization, and training pipeline. SCI Zone 3 · CCF C

SafeCodeRL: Security-Constrained Multi-Agent Reinforcement Learning for Trustworthy LLM-Generated IoT/CPS Software

Zhihua Wang, Junfan Chen, Zixiang Wei, Lan Lin, Guoxiang Tong†

† Corresponding author

First author · Sensors, 26(11), 3502

Code GenerationLLMAI SafetyMulti-Agent SystemsConstrained Reinforcement LearningIoT/CPS SecurityTrustworthy AIVulnerability Mitigation
SFMambaNet framework diagram showing pruning blocks, local spectral-geometric feature extraction, spectral-global aggregation, and verification. SCI Zone 1 · CCF A

Smooth Inliers, Erratic Outliers: Frequency-Aware Mamba for Two-View Correspondence Learning

Zhihua Wang, Yifeng Gao, Yunhao Feng, Rui Pan, Zhouyuan Ma, Baiheng Zhao, Zixing Chen, Yanping Li, Yizhang Liu, Xingjun Ma†

† Corresponding author

First author · Under review at IEEE Transactions on Image Processing (TIP) · arXiv preprint

Computer VisionCorrespondence PruningMambaState Space ModelFrequency DomainGraph Neural NetworksTwo-View Geometry
Conceptual model of carbon dynamics in mature mangrove ecosystems, showing net primary productivity, carbon sequestration, carbon efflux, and tidal carbon export pathways. Preprint

Research Support in Analysing Mangrove Responses to Climate Change: The Interplay of Anthropogenic Impacts and Blue Carbon Mitigation

Zhihua Wang

Sole author · UNDP / UNV review manuscript

UNDPUNVClimate ChangeBlue Carbon

Educations

  • 2027.09 – 2030.06 (expected) Fudan University · Incoming CS M.S. Student
  • 2023.09 – 2027.06 University of Shanghai for Science and Technology · B.Eng. in Computer Science and Technology (in progress)

Work Experience

2026.04 – present

AI Research Intern, Key Laboratory of Information Network Security, Ministry of Public Security (Third Research Institute, Shanghai)

  • Advisor: Songyang Wu
  • Project 1: Independently built a pipeline for joint analysis of webpage text, images, and URLs and localization of fraud evidence, producing one sole-first-author paper.
  • Project 2: Designed a lightweight algorithm for short-text risk-topic discovery, combining character and frozen semantic features to aggregate risk evidence from group chats and enable rapid CPU-based screening.
2026.01 – 2026.04

International Organization (United Nations Volunteers) - UNDP Data Research Intern (Online)

2023.06 – 2023.09

Meituan, Odd Jobs

Selected Research and Experience

2026.08 – 2026.11 Built MemHarmBench for cross-session memory poisoning and CST for CPU-based risk triage.

Research Intern, MemHarmBench and CST

Institute of Trustworthy Embodied AI (TEAI), Fudan University · FVL Laboratory · Shanghai Innovation Institute

Agent SafetyMemory PoisoningRisk TriageSource-Grounded EvidenceFirst Author
  • Advised by Xingjun Ma and Yu-Gang Jiang (Vice President, Fudan University).
  • MemHarmBench: Built an exposure–trigger benchmark for cross-session memory poisoning with 288 case environments (24 attack templates × 12 business scenarios) and 12 target categories. On samples retaining malicious rules, indirect attack success reached 59.38%–76.39%.
  • CST: Designed a lightweight algorithm for short-text risk-topic discovery, combining character-level and frozen semantic features to aggregate risk evidence from group chats for rapid CPU screening and source-grounded review.
2026.04 – 2026.08 Co-developed a multilingual fraud benchmark with expert-annotated evidence and explanations.

Research Intern, ScamWeb Multimodal Fraud Benchmark

Institute of Trustworthy Embodied Artificial Intelligence (TEAI), Fudan University & The Third Research Institute of the Ministry of Public Security

Multimodal BenchmarkCybersecurityGrounded UnderstandingTrustworthy AI
2026.03 – 2026.06 Integrated local agent sessions with controlled tool calls and runtime safety audits.

Research Intern, XSafeClaw Agent Runtime Safety

Institute of Trustworthy Embodied Artificial Intelligence (TEAI), Fudan University

TEAIAgent SafetyRuntime GovernanceOpen Source
  • Worked on XSafeClaw, an open-source safety platform for local and multi-runtime agent systems, at TEAI, Fudan University.
  • Worked under the guidance of Advisor Xingjun Ma, a Young Researcher and doctoral supervisor at Fudan University.
  • Implemented runtime integration for nanobot-style local agent sessions, including session discovery, controlled tool calls, and unified platform display.
  • Contributed to risk control workflows, validation, and documentation for explainable agent governance.
2026.01 – 2026.03 Combined CodeQL analysis, code context, and LLM judgement for vulnerability triage.

Research Intern, VulnSeeker

Fudan Software Engineering (CodeWisdom) Lab

CodeWisdomCodeQLLLM SecurityProgram Analysis
  • Conducted research at the Fudan Software Engineering (CodeWisdom) Lab, focusing on automated security analysis for generated and repository code.
  • Worked under the guidance of Lecturer Yi Li and collaborated with Qicai Chen, a Ph.D. student, on literature review, workflow design, and experimental validation.
  • Built a CodeQL-assisted vulnerability analysis workflow that combines static analysis, code context expansion, and LLM-based security judgement.
  • Designed prompt workflows for CodeQL and LLM interaction, including structured status codes for vulnerability triage and post-generation security inspection.
2026.01 – 2026.04 Reviewed mangrove responses to climate change and blue carbon mitigation through UNV.

International Organization Internship, UNDP-administered UNV Online Research Intern

Morobe Development Foundation Inc., Papua New Guinea

UNDPUNVClimate ChangeBlue Carbon
  • Completed an International Organization Internship through the UNDP-administered United Nations Volunteers (UNV) platform, supporting research on mangrove responses to climate change scenarios and blue carbon mitigation.
  • The United Nations Volunteers (UNV) programme is administered by the United Nations Development Programme (UNDP).
  • Synthesized literature on sea-level rise, coastal squeeze, nutrient loading, carbon sequestration, and national climate policy.
  • Produced a review manuscript titled Research Support in Analysing Mangrove Responses to Climate Change: The Interplay of Anthropogenic Impacts and Blue Carbon Mitigation.
2026.02 – 2026.05 Designed a five-agent, constraint-aware RL workflow for secure LLM code generation.

First-author Research, SafeCodeRL

Independent research collaboration

AI SafetyMulti-Agent SystemsConstrained RLSecure Code GenerationLLM Code GenerationIoT/CPS SecurityTrustworthy AI
  • Proposed SafeCodeRL, a multi-agent framework for dynamic safety constraints in LLM code generation.
  • Designed a closed-loop collaboration workflow across five agents and a PPO-style constraint-aware policy.
  • Reported a large reduction in high-risk vulnerable code generation while preserving functional correctness in the manuscript.
2025.09 – 2026.03 Explored spectral-frequency state space models for robust two-view correspondence pruning.

Research Intern, SFMambaNet

Fujian Key Laboratory of Network Computing and Intelligent Information Processing, Fuzhou University

Computer VisionCorrespondence PruningMambaState Space ModelsFrequency DomainTwo-View GeometryOutlier Rejection
2024.05 – 2025.07 Trained in algorithms and data structures; earned national and regional programming awards.

ACMer, ACM Programming Training Team

University of Shanghai for Science and Technology

ACMCompetitive ProgrammingAlgorithmsData Structures
  • Completed systematic training in algorithms, data structures, and contest problem solving.
  • Earned a National First Prize in the 2025 RAICOM Robot Developer Competition, a Silver Award at the 2025 ACM Shanghai Collegiate Programming Contest, and a National Second Prize in the 2025 LanQiao Cup C/C++ competition.

Awards

  • Silver Award, ACM Shanghai Collegiate Programming Contest
  • National First Prize, RAICOM Robot Developer Competition,
  • National Second Prize, LanQiao Cup C/C++ Programming Contest,
  • National First Prize, National Finals of the 9th National College Student Embedded Chip and System Design Competition,
  • National Second Prize, National Computer Competency Challenge (2 awards)
  • National Encouragement Scholarship, Five-time Recipient
  • Scholarships: First Class (2 awards), Second Class (3 awards), Third Class (2 awards)
  • National Third Prize, National English Competition for College Students,
  • Shanghai First Prize, National College Student Mathematics Competition,
  • First-author software copyright for a robust deep-learning watermark mobile application
  • Software Copyright: Code Security Analysis System Based on CodeQL and LLMs (First Author)

Services

Peer Review

Reviewer, NeurIPS 2026

Contributing to rigorous peer evaluation for research in machine learning and artificial intelligence.

Acknowledgements

I thank my teachers, mentors, and collaborators for their guidance and support, and my senior peers and friends for accompanying me along the way.

Visitors around the world

Enable JavaScript to display the map, or open the visitor statistics.
Locations are estimated from IP addresses and may reflect a proxy or VPN. MapMyVisitors · Privacy

Last updated:

Visits since the beginning