AI safety researcher

Z. Berkay Celik

Purdue University

Google Scholar dblp ORCID

Last 12 months7 papers

Risky behavior 1

AI safety papers from the last year

On this site: 18 papers

September 2026

Refusals That Bend: Measuring and Predicting Task Malleability in Embodied VLM Planners
Sep 30Risky behaviorarXiv ↗

August 2026

A Self-Explainable Deep Architecture for Security Applications
Aug 6arXiv ↗

June 2026

Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection
Jun 29arXiv ↗

May 2026

December 2025

Physical ID-Transfer Attacks against Multi-Object Tracking via Adversarial Trajectory
Dec 1arXiv ↗

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