AI safety researcher

Jinyuan Jia

Penn State University

Google Scholar dblp ORCID Homepage

Last 12 months12 papers

Attacks 4Evaluation and benchmarks 2

AI safety papers from the last year

On this site: 79 papers

September 2026

Climbing the Hill: Prompt Injection Red-Teaming Against Frontier Models with Curriculum Reinforcement Learning
Sep 27AttacksarXiv ↗

August 2026

LongPIBench: A Long-Context Benchmark for Prompt Injection
Aug 28Evaluation and benchmarksarXiv ↗
Agent Against Agent: An Agentic System for Automatic Prompt Injection Red Teaming
Aug 5AttacksarXiv ↗

May 2026

CleanBase: Detecting Malicious Documents in RAG Knowledge Databases
May 1arXiv ↗

April 2026

FlashRT: Towards Computationally and Memory Efficient Red-Teaming for Prompt Injection and Knowledge Corruption
Apr 30AttacksarXiv ↗
PIArena: A Platform for Prompt Injection Evaluation
Apr 9Evaluation and benchmarksarXiv ↗
TRUSTDESC: Preventing Tool Poisoning in LLM Applications via Trusted Description Generation
Apr 8arXiv ↗
AgentWatcher: A Rule-based Prompt Injection Monitor
Apr 1arXiv ↗

March 2026

November 2025

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