Xinyue Shen
Scholar

Xinyue Shen

Google Scholar ID: N4y3p8kAAAAJ
CISPA Helmholtz Center for Information Security
Trustworthy MLLLM/VLM Security and SafetySocial ComputingAgentic AI
Citations & Impact
All-time
Citations
1,746
 
H-index
11
 
i10-index
12
 
Publications
20
 
Co-authors
16
list available
Resume (English only)
Academic Achievements
  • - Awards: Best Machine Learning and Security Paper in Cybersecurity Award (2025), Machine Learning and Systems Rising Star (2025), KAUST Rising Star in AI (2025), Heidelberg Laureate Forum Young Researcher (2024)
  • - Publications: Including “Do Anything Now”, “Prompt Stealing Attacks Against Text-to-Image Generation Models”, “HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns”
  • - Other Achievements: Research acknowledged by Google, Microsoft, and OpenAI, integrated into major AI systems such as Nvidia’s Garak, OpenAI’s GPT-4.5, o3-mini, and o1, with 3K+ Github stars and 45K+ downloads on HuggingFace
Research Experience
  • - Work Experience: Two years as an algorithm engineer at Alibaba before joining CISPA
  • - Research Directions: Understanding real-world AI system misuses; proactively detecting and mitigating misused outputs from AI systems; identifying emerging security risks like prompt stealing attack and knowledge file leakage
Education
  • - Ph.D.: CISPA Helmholtz Center for Information Security (Germany), advised by Michael Backes and Yang Zhang
  • - B.S.: University of Electronic Science and Technology of China (UESTC)
Background
  • - Research Interests: Trustworthy AI, with a focus on the security, safety, and responsibility of generative AI systems
  • - Personal Introduction: On the academic job market for the 2025-2026 cycle
Miscellany
  • - Teaching and Mentoring: Passionate about teaching, guest lecturer for three courses at CISPA & Saarland University, hosting weekly office hours to help students start research or pursue a Ph.D.
  • - Personal Interests: Writing sci-fi novels and popular-science articles to make AI and Cybersecurity more accessible to the general public