AI safety researcher

Jiguo Yu

Google Scholar dblp ORCID

Last 12 months3 papers

Defenses 1Attacks 1

AI safety papers from the last year

On this site: 8 papers

September 2026

Robust Dynamic Expansion for Continual Learning under Backdoor Attacks via Purification and Selective Recovery
Sep 6DefensesarXiv ↗
Implicit Manipulation for Skill Selection in LLM Agents with Semantic Matching
Sep 2AttacksarXiv ↗

August 2026

FL-OA: A Byzantine-Robust Federated Learning Framework with Outsourced Auditing for Intelligent Devices
Aug 2arXiv ↗

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