AI safety researcher

Keke Gai

Google Scholar dblp ORCID

Latest AI safety papers

On this site: 10 papers

August 2025

A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learning
Aug 14arXiv ↗

July 2025

LLAMA: Multi-Feedback Smart Contract Fuzzing Framework with LLM-Guided Seed Generation
Jul 16arXiv ↗

April 2025

AGATE: Stealthy Black-box Watermarking for Multimodal Model Copyright Protection
Apr 28arXiv ↗
PCDiff: Proactive Control for Ownership Protection in Diffusion Models with Watermark Compatibility
Apr 16arXiv ↗

February 2025

Secure and Efficient Watermarking for Latent Diffusion Models in Model Distribution Scenarios
Feb 18arXiv ↗

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