RMF: A Risk Measurement Framework for Machine Learning Models
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 12 of its 28 references that are in the map. First posted on arXiv 15 Jun 2024.
Builds on
12 of 28 references.
References · 12
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2017A Closer Look at Memorization in Deep Networkscited by 936
- 2016Practical Black-Box Attacks against Machine Learningcited by 893
- 2019Hidden Trigger Backdoor Attackscited by 359
- 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 219
- 2018Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approachcited by 181
- 2020Witches' Brew: Industrial Scale Data Poisoning via Gradient Matchingcited by 156
- 2019TBT: Targeted Neural Network Attack with Bit Trojancited by 112
- 2020An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networkscited by 92
- 2018Backdooring Convolutional Neural Networks via Targeted Weight Perturbationscited by 66
- 2019RowHammer: A Retrospectivecited by 19
- 2020Risk Management Framework for Machine Learning Securitycited by 1
Built on by
Not cited yet.