AI safety researcher

Shuang Song

Google Research

Google Scholar dblp

Attacks 1

Latest AI safety papers

On this site: 20 papers

October 2025

The Attacker Moves Second: Stronger Adaptive Attacks Bypass Defenses Against Llm Jailbreaks and Prompt Injections
Oct 10AttacksarXiv ↗

May 2025

Lessons from Defending Gemini Against Indirect Prompt Injections
May 20arXiv ↗

March 2025

Large Language Models Can Verbatim Reproduce Long Malicious Sequences
Mar 21arXiv ↗

April 2023

Advancing Differential Privacy: Where We Are Now and Future Directions for Real-World Deployment
Apr 14arXiv ↗

February 2023

Multi-Task Differential Privacy Under Distribution Skew
Feb 15arXiv ↗

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