AI safety researcher

Shiqing Ma

University of Massachusetts Amherst

Google Scholar dblp OpenReview ORCID Homepage

Last 12 months4 papers

Evaluation and benchmarks 1

AI safety papers from the last year

On this site: 44 papers

April 2026

Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets
Apr 24arXiv ↗

February 2026

Trojans in Artificial Intelligence (TrojAI) Final Report
Feb 6arXiv ↗

January 2026

False Friends in the Shell: Unveiling the Emoticon Semantic Confusion in Large Language Models
Jan 12Evaluation and benchmarksarXiv ↗

November 2025

PROMPTMINER: Black-Box Prompt Stealing against Text-to-Image Generative Models via Reinforcement Learning and Fuzz Optimization
Nov 27arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.