About Me

I am exploring trustworthy artificial intelligence under the close guidance of Prof. Dr. Yang Zhang and Prof. Dr. Michael Backes. I am currently pursuing my Ph.D. at CISPA Helmholtz Center for Information Security, Germany. I hold a Master's degree from Uppsala University, Sweden, and a Bachelor's degree from Shanghai Jiao Tong University, China.

Research Interests

  • Generative Machine Learning
  • Trustworthy Artificial Intelligence

News

  • [08-2026] Our paper JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring has been accepted by EMNLP'26 (Budapest, Hungary).
  • [08-2026] Our three papers Behavior Carries Over: An AI Sandbagging Detection Method Inspired by Honest Inertia, RW2Unsafe: Towards More Accurate Real-World Unsafe Generation Evaluation for T2I Models, and GuardrailAgent: An Agentic Framework for Jailbreak Defense have been accepted by EMNLP'26 Findings (Budapest, Hungary).
  • [05-2026] I was recognized as a Gold Reviewer for ICML'26 (Seoul, South Korea).
  • [02-2026] Our paper When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm has been accepted by CVPR'26 (Denver, US).
  • [05-2025] Our paper JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs has been accepted by ACL'25 (Vienna, Austria).
  • [03-2025] Our paper Neeko: Model Hijacking Attacks Against GANs has been accepted by ICME'25 (Nantes, France).
  • [03-2025] Our paper Generated Data with Fake Privacy: Hidden Dangers of Fine-Tuning Large Language Models on Generated Data has been accepted by USENIX Security'25 (Seattle, US).
  • [09-2024] Our paper Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models has been accepted by EMNLP'24 (Miami, US).
  • [03-2024] Our paper Games and Beyond: Analyzing the Bullet Chats of Esports Livestreaming has been accepted by ICWSM'24 (Buffalo, US).
  • [09-2023] With the support of Prof. Dr. Yang Zhang and Prof. Dr. Michael Backes, I successfully passed my Qualifying Exam.
Flag Counter Flag Counter

Resume

Education

  1. Ph.D.

    CISPA Helmholtz Center for Information Security / Saarland University, Germany Nov 2022 — Present

    Advisor: Prof. Dr. Yang Zhang
    Supervisor: Prof. Dr. Michael Backes

  2. M.Sc.

    Uppsala University, Sweden

    Advisor: Prof. Dr. Salman Toor

  3. B.Sc.

    Shanghai Jiao Tong University, China

Experience

  1. Data Engineer (Intern)

    Scaleout, Uppsala, Sweden Nov 2021 — Jan 2022

  2. Data Engineer (Intern)

    Ericsson, Shanghai, China Jun 2021 — Sep 2021

    Mentor: Daniel Chen

  3. Assistant Manager of Product Development (Intern)

    Haitong Securities, Shanghai, China Jun 2016 — Sep 2016

    Mentor: Yuanhua (Inni) Shi

Publications

Also find my articles on Google Scholar.

  • JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring

    Junjie Chu, Mingjie Li, Ziqing Yang, Ye Leng, Chenhao Lin, Chao Shen, Michael Backes, Yun Shen, Yang Zhang

    Selected as an EMNLP'26 oral

    EMNLP'26
    Paper Website

  • Behavior Carries Over: An AI Sandbagging Detection Method Inspired by Honest Inertia

    Junjie Chu, Mingjie Li, Zeyuan Chen, Ye Leng, Yisen Wang, Michael Backes, Yang Zhang

    EMNLP'26 Findings

  • RW2Unsafe: Towards More Accurate Real-World Unsafe Generation Evaluation for T2I Models

    Ye Leng, Junjie Chu, Mingjie Li, Yun Shen, Michael Backes, Yang Zhang

    EMNLP'26 Findings

  • GuardrailAgent: An Agentic Framework for Jailbreak Defense

    Tianze Chang, Junjie Chu, Yixin Wu, Michael Backes, Yang Zhang

    EMNLP'26 Findings

  • When Understanding Becomes a Risk: Authenticity and Safety Risks in the Emerging Image Generation Paradigm

    Ye Leng*, Junjie Chu*, Mingjie Li, Chenhao Lin, Chao Shen, Michael Backes, Yun Shen, Yang Zhang

    * Co-first authors. Selected as a CVPR'26 highlight

    CVPR'26
    Paper

  • JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs

    Junjie Chu, Yugeng Liu, Ziqing Yang, Xinyue Shen, Michael Backes, Yang Zhang

    Selected as an ACL'25 oral (243/1699 accepted papers)

    ACL'25
    Paper Website

  • Neeko: Model Hijacking Attacks Against Generative Adversarial Networks

    Junjie Chu, Yugeng Liu, Xinlei He, Michael Backes, Yang Zhang, Ahmed Salem

    ICME'25
    Paper PDF

  • Generated Data with Fake Privacy: Hidden Dangers of Fine-Tuning Large Language Models on Generated Data

    Atilla Akkus, Masoud Poorghaffar Aghdam, Mingjie Li, Junjie Chu, Michael Backes, Yang Zhang, Sinem Sav

    USENIX Security'25
    Paper

  • Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models

    Junjie Chu, Zeyang Sha, Michael Backes, Yang Zhang

    Selected as an EMNLP'24 oral; presented as a poster due to visa-related issues.

    EMNLP'24
    Paper

  • Games and Beyond: Analyzing the Bullet Chats of Esports Livestreaming

    Yukun Jiang, Xinyue Shen, Rui Wen, Zeyang Sha, Junjie Chu, Yugeng Liu, Michael Backes, Yang Zhang

    ICWSM'24
    Paper

  • Efficient Resource Scheduling for Distributed Infrastructures Using Negotiation Capabilities

    Junjie Chu, Prashant Singh, Salman Toor

    CLOUD'23
    Paper

  • Energy Harvesting of Air-Borne Sound by Using Layered Acoustic Metamaterials

    Jiajie Xu, Xiaole Wang, Junjie Chu, Zhenyu Huang

    ICSV'18
    PDF

Service

Reviewer / Program Committee Member

  1. Conferences

    • 2027: AAAI, SaTML
    • 2026: ACL ARR May/August, ICME, ICML (Gold Reviewer), SaTML
    • 2025: ACL ARR May/July/October, ICME, WWW

  2. Transactions / Journals

    • TDSC, TIFS, TOPS, TOSEM, IEEE Secur. Priv., Neural Netw.

Teaching

  1. 2022-Spring

    Teaching Assistant, Uppsala University, IT Department
    1DL034 Introduction to Machine Learning
    1TD069 Data Engineering I

Misc.

Gallery of My Cats

  • Riki
    Riki
  • Jelly
    Jelly
  • Sleeping
    Sleeping

Visited Places