AI safety researcher

Shouling Ji

Zhejiang University

Google Scholar dblp ORCID Homepage

Last 12 months32 papers

Defenses 5Attacks 2Other 1Analysis and theory 1Evaluation and benchmarks 1

AI safety papers from the last year

On this site: 114 papers

October 2026

FedGraph: Defending Federated Large Language Model Fine-Tuning Against Backdoor Attacks via Graph-Based Aggregation
Oct 13DefensesarXiv ↗
StateWise: Diagnosing and Repairing Persistent Operational State Before Agent Actions
Oct 4DefensesarXiv ↗

September 2026

HazardAuditor: From Executable Threats to Safer Computer-Use Agents
Sep 14DefensesarXiv ↗
Safety in Self-Evolving Agents: A Survey
Sep 8OtherarXiv ↗
A Finger on the Scale: Covert Policy Steering through Agentic Skills
Sep 2AttacksarXiv ↗

August 2026

July 2026

June 2026

Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies
Jun 22Analysis and theoryarXiv ↗
Understanding and Mitigating Prompt Leaking Attacks in Real-World LLM-Based Applications
Jun 17DefensesarXiv ↗
Customization under Fire: Plugin Poisoning in Text-to-Image Ecosystem
Jun 8arXiv ↗

May 2026

April 2026

March 2026

February 2026

TrapSuffix: Proactive Defense Against Adversarial Suffixes in Jailbreaking
Feb 6arXiv ↗

January 2026

December 2025

November 2025

Synthetic Voices, Real Threats: Evaluating Large Text-to-Speech Models in Generating Harmful Audio
Nov 14arXiv ↗

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