AI safety researcher

Carsten Maple

University of Warwick

Google Scholar dblp ORCID Homepage

Last 12 months11 papers

Defenses 1Attacks 1

AI safety papers from the last year

On this site: 23 papers

September 2026

Certified Multi-Source Integrity for Structured Agent Actions
Sep 28DefensesarXiv ↗
Probabilistic Robustness-driven Universal Adversarial Perturbations with Explainability against Deep Reinforcement Learning-based Intrusion Detection System
Sep 24arXiv ↗
Empirical Auditing of Edge-Private Graph Generators
Sep 21arXiv ↗

July 2026

May 2026

March 2026

November 2025

Non-Parametric Probabilistic Robustness: A Conservative Risk Estimator under Unknown Perturbation Distributions
Nov 21arXiv ↗

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