AI safety researcher

Joshua Saxe

Google Scholar dblp

Other 2Evaluation and benchmarks 1

Latest AI safety papers

On this site: 12 papers

September 2025

CyberSOCEval: Benchmarking LLMs Capabilities for Malware Analysis and Threat Intelligence Reasoning
Sep 24Evaluation and benchmarksarXiv ↗

July 2025

Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
Jul 15OtherarXiv ↗

May 2025

LlamaFirewall: An open source guardrail system for building secure AI agents
May 6arXiv ↗

August 2024

CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models
Aug 2arXiv ↗

July 2024

The Llama 3 Herd of Models
Jul 31OtherarXiv ↗

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