LabCompass

Xinyue Shen

Computer Science · Indiana University

OpenAlex ORCID
Adversarial Robustness in Machine LearningTopic ModelingHate Speech and Cyberbullying DetectionScientific Computing and Data ManagementInformation and Cyber Security

Publications

102

Citations

867

Est. group size

—

Recurring co-author estimate

Active years

17

Publishing since 2010

Research summary
AI-generated

Xinyue Shen works on the security and safety of modern artificial intelligence systems, especially large language models (the AI behind chatbots) and AI agents. Recent projects examine how these systems can be attacked or misused, how their training can be manipulated, and how to evaluate their safety, along with related studies of online harmful content. The work sits at the intersection of machine learning and cybersecurity.

Large language model security and safetyAI agents and multi-agent systemsAttacks on machine learning models (e.g., membership inference)Safety benchmarking and evaluation of AIDetection of harmful and deceptive online content

Publication activity has grown sharply, rising from a few papers per year before 2022 to double digits from 2023 onward and peaking in the most recent year.

Generated by claude-opus-4-8 from public bibliographic data · Jul 11, 2026

Publication cadence
Publications per year over the last 10 years — averaging 17.6/year recently
2017: 2 publications172018: 2 publications18192020: 1 publication202021: 2 publications212022: 3 publications222023: 17 publications232024: 11 publications242025: 19 publications252026: 38 publications3826
Recent publications
Publishes in
  • arXiv (Cornell University)×27
  • CISPA Helmholtz Center×17
  • Figshare×6
  • Zenodo (CERN European Organization for Nuclear Research)×4
  • Zhongguo jiaqin×3

This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.

Last updated Jul 11, 2026.

Claim or correct this profile