AI safety researcher

Wei Yang Bryan Lim

Nanyang Technological University

Google Scholar dblp ORCID

Last 12 months15 papers

Attacks 6Other 1Defenses 1

AI safety papers from the last year

On this site: 21 papers

September 2026

VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agents
Sep 29AttacksarXiv ↗
Concept Score Relearning: A Unified Cross-Architecture Attack on Concept Erasure
Sep 27AttacksarXiv ↗
Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions
Sep 23AttacksarXiv ↗

August 2026

May 2026

February 2026

December 2025

Disrupting Hierarchical Reasoning: Adversarial Protection for Geographic Privacy in Multimodal Reasoning Models
Dec 9arXiv ↗

November 2025

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