AI safety researcher

Kun He

Google Scholar dblp ORCID Homepage

Attacks 1

Latest AI safety papers

On this site: 28 papers

November 2025

Parameter Interpolation Adversarial Training for Robust Image Classification
Nov 2arXiv ↗

October 2025

Invisible to Humans, Triggered by Agents: Stealthy Jailbreak Attacks on Mobile Vision-Language Agents
Oct 9AttacksarXiv ↗

August 2025

ViT-EnsembleAttack: Augmenting Ensemble Models for Stronger Adversarial Transferability in Vision Transformers
Aug 17arXiv ↗

August 2024

Feedback-based Modal Mutual Search for Attacking Vision-Language Pre-training Models
Aug 27arXiv ↗

January 2024

Fast Adversarial Training against Textual Adversarial Attacks
Jan 23arXiv ↗

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