AI safety researcher

Tianqing Zhu

Google Scholar dblp ORCID

Last 12 months23 papers

Defenses 3Attacks 2

AI safety papers from the last year

On this site: 88 papers

October 2026

MARCO: The Radioactive Watermark for Protein Generative Models
Oct 6DefensesarXiv ↗
LiBRA: Detection-Aware Image Watermark Removal via Bidirectional Latent Optimization
Oct 2AttacksarXiv ↗

September 2026

First Token Matters: Understanding Safety Collapse in Large Reasoning Models
Sep 16arXiv ↗
RISA: Response Inspection and Selective Actions for Refusal Calibration in Large Language Models
Sep 1DefensesarXiv ↗

August 2026

BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes
Aug 8arXiv ↗

June 2026

May 2026

April 2026

March 2026

January 2026

Forgetting Similar Samples: Can Machine Unlearning Do it Better?
Jan 11arXiv ↗

December 2025

Black-Box Auditing of Quantum Model: Lifted Differential Privacy with Quantum Canaries
Dec 16arXiv ↗

November 2025

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