RMF: A Risk Measurement Framework for Machine Learning Models

Jan Schröder, Jakub Breier
6/15/2024
cs.CRcs.AIcs.LG

No confident code implementation found for this paper.

Abstract

Machine learning (ML) models are used in many safety- and security-critical applications nowadays. It is therefore important to measure the security of a system that uses ML as a component. This paper focuses on the field of ML, particularly the security of autonomous vehicles. For this purpose, a technical framework will be described, implemented, and evaluated in a case study. Based on ISO/IEC 27004:2016, risk indicators are utilized to measure and evaluate the extent of damage and the effort required by an attacker. It is not possible, however, to determine a single risk value that represents the attacker's effort. Therefore, four different values must be interpreted individually.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

FRAME : Comprehensive Risk Assessment Framework for Adversarial Machine Learning Threats

84% match2025

Safety Monitoring of Machine Learning Perception Functions: a Survey

83% match2024

Learning Run-time Safety Monitors for Machine Learning Components

82% match2024

Threats, Vulnerabilities, and Controls of Machine Learning Based Systems: A Survey and Taxonomy

82% match2023

Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks

80% match2025

Assuring the Safety of Reinforcement Learning Components: AMLAS-RL

80% match2025

Cite this paper

@article{schrder2024rmf,
  title  = {RMF: A Risk Measurement Framework for Machine Learning Models},
  author = {Jan Schröder and Jakub Breier},
  year   = {2024},
  eprint = {2406.12929},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.12929v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.12929.svg)](https://codeofpaper.com/paper/2406.12929)

Discussion