Jingzhi Jiang 蒋静之

Biography

Hi! I am a Computer Science student at UC Berkeley (Class of 2026) with a 4.0 GPA. I focus on AI for security and work closely with Prof. David Wagner and Prof. Dawn Song on autonomous agent benchmarking, large-scale fuzzing, and real-time threat detection.

Outside of security, I working with Prof.Carl Bottiger in the Eric & Wendy Schmidt Center on reinforcement learning for environmental decision-making,

Research Experience

David Wagner Research Group

Computer Security Researcher · Berkeley, CA

Jan 2025 – Present
  • Automated fuzz corpus collection with LLM to uncover vulnerabilities across OSS projects.
  • Authored Scrapy + Search API tooling to locate seed files with diverse characteristics.
  • Containerized OSS-Fuzz, LibFuzzer, and Magma benchmark pipelines for multi-corpus experimentation.
  • Co-authored the SeedAIchemy paper for the 2025 LLM4Sec Workshop at ICDM.
  • Generated LLM-based log rules that flag malicious host activity in real time.

Dawn Song Research Group

Computer Security Researcher · Berkeley, CA

Oct 2025 – Present
  • Lead developer for e2e-cyber-bench, a 1,500+ instance benchmark for evaluating AI agents on real-world vulnerability analysis tasks.
  • Integrated historical CVEs from 188 large projects and automated reproducible setups for each target.
  • Built fuzzing and unit-test harnesses that evaluate whether agents successfully patch vulnerabilities.

Eric & Wendy Schmidt Center for Data Science & Environment

Machine Learning Researcher · Berkeley, CA

Apr 2024 – Present
  • Determined optimal green crab mitigation strategies with RecurrentPPO and other deep RL approaches.
  • Fine-tuned agents and executed Optuna-based hyperparameter searches.
  • Built Gymnasium simulations to visualize population dynamics over time.
  • Crafted training environments with varied observations and randomness to improve robustness.

Working Experience

KPMG

Software Development Intern · Shanghai, China

2024
  • Implemented a Python + MongoDB storage backend to accelerate metadata queries for the patch intelligence platform.
  • Developed a PDF-to-text prototype with image and data extraction to improve downstream document ingestion accuracy.
  • Completed a graphRAG workflow powered by Qwen, Microsoft graphRAG, and LM Studio for contextual retrieval.
  • Benchmarked Text-to-SQL models on private datasets using Hugging Face and LlamaIndex.

Floras & Berkeley SkyDeck

Full Stack Software Development Intern · Berkeley, CA

2023
  • Designed a website for Floras showcasing 200 sustainable projects with searching and filtering features.
  • Implemented the storage backend with Python and MongoDB for fast metadata queries from the Patch database.
  • Developed front-end website integration using Flask, HTML, JavaScript, and CSS.

Publications

SeedAIchemy: LLM-Driven Seed Corpus Generation for Fuzzing

Aidan W., Norah A., Jingzhi J., Andrew J., Karen S., Andy Z., Basel A., David W.

LLM4Sec Workshop @ ICDM 2025
  • Demonstrated how LLMs generate high-quality seed corpora that boost fuzzing code coverage and exploit discovery.
  • Benchmarked across OSS-Fuzz targets and released evaluation tooling for the community.

Teaching Experience

UC Berkeley CSM

CS61C Mentor · Berkeley, CA

Jan 2024 – May 2024
  • Ran weekly small-group sessions covering RISC-V, C, CPU design, and cache behavior.
  • Prepared walkthroughs and practice problems for exam review sessions.

UC Berkeley EECS

CS61B Academic Intern · Berkeley, CA

Aug 2024 – Dec 2024
  • Supported weekly teaching sections and helped 100+ students to reinforce core data-structure concepts.
  • Triaged lab queues, debugged Java code, and curated study notes for upcoming exams.

Highlighted Projects

WebBot

Chrome Extension · Python & JavaScript

Dec 2024 – Feb 2025

Chrome extension that pipes any page through Azure-hosted LLM + RAG pipelines, shipped with Flask APIs and a React UI.

Computer Vision Projects

CS180 Portfolio · Panoramas · NeRF · Diffusion

2025

A suite of CS180 projects: panorama building, NeRF reconstruction, and diffusion-model training, all documented in the linked portfolio.

e2e-cyber-bench

Cybersecurity Agent Benchmark

2025

1,500+ CVE-derived evaluation tasks with reproducible scripts for benchmarking autonomous security agents.

SeedAIchemy

LLM-Driven Fuzzing

2025

LLM-powered corpus generator that boosts fuzzing; a LLM4Sec workshop paper.

CodaBot

Team of 2 · Go

Sep 2024 – Nov 2024

Secure Go-based file sharing system with HMAC, RSA, AES-CTR, and constant-bandwidth append algorithms.

RL4GreenCrab

Deep RL for Green Crab Population Control

2024 – Present

DRL agents, Gymnasium environments, and Optuna tuning scripts for sustainable green crab invasion control.

detailed project list.

Skills

  • Python (NumPy, pandas)
  • Java
  • C
  • Go
  • SQL / MySQL
  • RISC-V
  • HTML & CSS
  • JavaScript
  • React
  • Docker
  • Firebase
  • MongoDB
  • Hugging Face
  • LlamaIndex
  • LangChain
  • PyTorch
  • Scikit-learn
  • Azure
  • Linux