LabCompass

Mengxin Zheng

Computer Science · Indiana University

OpenAlex ORCID
Adversarial Robustness in Machine LearningCryptography and Data SecurityAdvanced Malware Detection TechniquesNatural Language Processing TechniquesAdvanced Steganography and Watermarking Techniques

Publications

48

Citations

425

Est. group size

—

Recurring co-author estimate

Active years

12

Publishing since 2015

Research summary
AI-generated

Mengxin Zheng works in computer science with a focus on the security and trustworthiness of machine learning systems, especially large language models (LLMs). Recent projects examine attacks and defenses such as text watermarking, hidden 'Trojan' backdoors, jailbreaks that bypass safety controls, and privacy-preserving inference, along with hardware-level security for AI accelerators and applications of quantum and cryptographic methods.

Machine learning security (backdoors, Trojans, jailbreaks)LLM watermarking and content attributionPrivacy-preserving and encrypted computationHardware and accelerator securityQuantum computing and cryptography

Publication activity grew sharply from 2019 onward, peaking around 2023-2024 and remaining high, averaging about 8 papers per year over the last five years.

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

Publication cadence
Publications per year over the last 10 years — averaging 8.0/year recently
17182019: 1 publication192020: 4 publications202021: 2 publications212022: 3 publications222023: 12 publications232024: 13 publications13242025: 10 publications252026: 2 publications26
Recent publications
Publishes in
  • arXiv (Cornell University)×15
  • Advanced Fiber Materials×2
  • Advanced Engineering Materials×2
  • SSRN Electronic Journal×2
  • Lab on a Chip×1

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