AI safety researcher

Benjamin I. P. Rubinstein

University of Melbourne

Google Scholar dblp OpenReview ORCID Homepage

Last 12 months8 papers

Interpretability 1Defenses 1

AI safety papers from the last year

On this site: 37 papers

June 2026

Room for Error: Large-Scale Simulation of Over-the-Air Acoustic Attacks
Jun 26arXiv ↗
What Was That Again? Certified Robustness for Automatic Speech Recognition
Jun 26arXiv ↗
Halt Fast! Early Stopping for Certified Robustness
Jun 26arXiv ↗
Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attacks
Jun 5arXiv ↗
Multilingual Unlearning in LLMs: Transfer, Dynamics, and Reversibility
Jun 2InterpretabilityarXiv ↗

May 2026

Watermarks Attack Watermarks: Re-Watermarking as a Generic Removal Strategy
May 16arXiv ↗

February 2026

Semantic-aware Adversarial Fine-tuning for CLIP
Feb 12DefensesarXiv ↗

December 2025

Where is the Watermark? Interpretable Watermark Detection at the Block Level
Dec 17arXiv ↗

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