English CV

Last updated: PDF · 2 pages

If the preview is unavailable, use the buttons above to open or download the PDF.

中文简历

Last updated: PDF · 2 pages

If the preview is unavailable, use the buttons above to open or download the PDF.

Concise Chinese CV Expand to view

Last updated: · PDF · 1 page

If the preview is unavailable, use the buttons above to open or download the PDF.

View web CV

Education

2023.09 – 2027.06

B.Eng. in Computer Science and Technology (in progress)

University of Shanghai for Science and Technology · School of Optical-Electrical and Computer Engineering

  • Class of 2023; currently a senior undergraduate.
  • Core academic interests: software engineering, web application development, artificial intelligence, algorithms, and high-performance programming.

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

Research and Internship Experience

2026.08 – 2026.11

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

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

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

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

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

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

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

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.

Publications and Manuscripts

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.
Figure 1 · Cross-session prompt injection can remain hidden behind successful task completion.

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 · Submitted to WWW 2027 · 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.
CST framework · Original figure from the paper.

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 · Submitted to WWW 2027 · arXiv preprint ·

Risk TriageSource-Grounded EvidenceWeb DiscussionsMultilingual NLPCPU Inference
ScamWeb dataset overview showing data sources, webpage collection and recovery, processed multimodal artifacts, expert annotations, dataset composition, and representative samples.
Dataset and annotation overview

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

Nan Li*, Zhihua Wang*, 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
SafeCodeRL framework diagram showing IoT/CPS contexts, a five-agent closed loop, constraint-aware optimization, and training pipeline.
Framework overview

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 ·

SCI Zone 3CCF C
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.
Framework overview

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 ·

SCI Zone 1CCF A
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.
Framework overview

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

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.

Skills

Research

AI safetyLLM agentsprogram analysiscomputer visionscientific writing

Programming

C/C++PythonJavaTypeScriptAstro

Tools

CodeQLGitLaTeXOverleafPyTorchTensorFlow

Language

English technical readingCET-4 and CET-6 passed

Learning Map

AI Safety and LLM Agents

88%

Focused on agent runtime governance, safety-constrained code generation, tool-call auditing, and human-in-the-loop risk control.

Software Security and Program Analysis

84%

Built workflows around CodeQL, LLM-assisted vulnerability judgement, code context expansion, and post-generation security inspection.

Deep Learning and Multimodal Intelligence

82%

Studied neural architectures for visual correspondence, spectral-frequency modeling, state space models, and robust image watermarking.

Algorithms and Systems Programming

86%

Maintains strong C/C++ foundations through algorithmic problem solving, contest-style implementation, and performance-conscious coding.

Scientific Writing and Research Methodology

80%

Practices literature synthesis, experiment design, manuscript organization, and cross-domain research communication.

Web Engineering and Research Prototyping

78%

Uses TypeScript, Python, Git, LaTeX, and static-site tooling to turn research ideas into reproducible public artifacts.