AI safety researcher

Fei Sun

Chinese Academy of Sciences

Google Scholar dblp ORCID Homepage

Latest AI safety papers

On this site: 14 papers

October 2025

A Survey on Unlearning in Large Language Models
Oct 29arXiv ↗

July 2025

LLM4MEA: Data-free Model Extraction Attacks on Sequential Recommenders via Large Language Models
Jul 22arXiv ↗

October 2024

Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
Oct 30arXiv ↗

September 2024

Improving the Shortest Plank: Vulnerability-Aware Adversarial Training for Robust Recommender System
Sep 26arXiv ↗

August 2024

Accelerating the Surrogate Retraining for Poisoning Attacks against Recommender Systems
Aug 20arXiv ↗

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