AI safety researcher

Siddharth Garg

Google Scholar dblp OpenReview Homepage

Last 12 months3 papers

Analysis and theory 2

AI safety papers from the last year

On this site: 33 papers

October 2026

Which Image Property Carries the Jailbreak? A Controlled Dissection of Image-to-Text Jailbreaks
Oct 4Analysis and theoryarXiv ↗
Where Does the Audio Jailbreak Live? A Controlled Frequency-Depth Audit of AdvWave-P on Qwen2-Audio
Oct 4Analysis and theoryarXiv ↗

April 2026

Surgical Repair of Insecure Code Generation in LLMs
Apr 17arXiv ↗

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