Quantifying CBRN Risk in Frontier Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kumar, Divyanshu, Birur, Nitin Aravind, Baswa, Tanay, Agarwal, Sahil, Harshangi, Prashanth
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915573777039360
author Kumar, Divyanshu
Birur, Nitin Aravind
Baswa, Tanay
Agarwal, Sahil
Harshangi, Prashanth
author_facet Kumar, Divyanshu
Birur, Nitin Aravind
Baswa, Tanay
Agarwal, Sahil
Harshangi, Prashanth
contents Frontier Large Language Models (LLMs) pose unprecedented dual-use risks through the potential proliferation of chemical, biological, radiological, and nuclear (CBRN) weapons knowledge. We present the first comprehensive evaluation of 10 leading commercial LLMs against both a novel 200-prompt CBRN dataset and a 180-prompt subset of the FORTRESS benchmark, using a rigorous three-tier attack methodology. Our findings expose critical safety vulnerabilities: Deep Inception attacks achieve 86.0\% success versus 33.8\% for direct requests, demonstrating superficial filtering mechanisms; Model safety performance varies dramatically from 2\% (claude-opus-4) to 96\% (mistral-small-latest) attack success rates; and eight models exceed 70\% vulnerability when asked to enhance dangerous material properties. We identify fundamental brittleness in current safety alignment, where simple prompt engineering techniques bypass safeguards for dangerous CBRN information. These results challenge industry safety claims and highlight urgent needs for standardized evaluation frameworks, transparent safety metrics, and more robust alignment techniques to mitigate catastrophic misuse risks while preserving beneficial capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2510_21133
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Quantifying CBRN Risk in Frontier Models
Kumar, Divyanshu
Birur, Nitin Aravind
Baswa, Tanay
Agarwal, Sahil
Harshangi, Prashanth
Cryptography and Security
Artificial Intelligence
Frontier Large Language Models (LLMs) pose unprecedented dual-use risks through the potential proliferation of chemical, biological, radiological, and nuclear (CBRN) weapons knowledge. We present the first comprehensive evaluation of 10 leading commercial LLMs against both a novel 200-prompt CBRN dataset and a 180-prompt subset of the FORTRESS benchmark, using a rigorous three-tier attack methodology. Our findings expose critical safety vulnerabilities: Deep Inception attacks achieve 86.0\% success versus 33.8\% for direct requests, demonstrating superficial filtering mechanisms; Model safety performance varies dramatically from 2\% (claude-opus-4) to 96\% (mistral-small-latest) attack success rates; and eight models exceed 70\% vulnerability when asked to enhance dangerous material properties. We identify fundamental brittleness in current safety alignment, where simple prompt engineering techniques bypass safeguards for dangerous CBRN information. These results challenge industry safety claims and highlight urgent needs for standardized evaluation frameworks, transparent safety metrics, and more robust alignment techniques to mitigate catastrophic misuse risks while preserving beneficial capabilities.
title Quantifying CBRN Risk in Frontier Models
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2510.21133