Who Cited It

On Assessing ML Model Robustness: A Methodological Framework (Academic Track)

2025 · OASIcs : OpenAccess Series in Informatics · 4,755 citations · 4 from inside this corpus

No author records on this work.

Due to their uncertainty and vulnerability to adversarial attacks, machine learning (ML) models can lead to severe consequences, including the loss of human life, when embedded in safety-critical systems such as autonomous vehicles. Therefore, it is crucial to assess the empirical robustness of such models before integrating them into these systems. ML model robustness refers to the ability of an ML model to be insensitive to input perturbations and maintain its performance. Against this background, the Confiance.ai research program proposes a methodological framework for assessing the empirical robustness of ML models. The framework encompasses methodological processes (guidelines) captured in Capella models, along with a set of supporting tools. This paper aims to provide an overview of this framework and its application in an industrial setting.

On Assessing ML Model Robustness: A Methodological Framework (Academic Track) (2025)On Assessing ML Model Robustn…Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey (2018)Threat of Adversarial Attacks…Shortcut learning in deep neural networks (2020)Shortcut learning in deep neu…Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks (2018)Feature Squeezing: Detecting …Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks (2019)Neural Cleanse: Identifying a…
4 of 4 neighbouring works in this corpus. Blue is what this paper cites; orange is what cites it, and a dashed line is one neighbour citing another. Only the largest labels are drawn — every node carries its full title on hover.
this paper works it cites works citing it node size = global citations · hover for the full title

Citation edge evidence

Each row is directed from the citing work to the cited work. Source status remains readable without the interactive graph.

What cites it, inside the corpus

PaperYearCited
Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey20182,090
Shortcut learning in deep neural networks20202,040
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks20181,882
Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks20191,404

Links

Download BibTeX · Download RIS · DOI · Open access copy · OpenAlex record

Topics

Adversarial Robustness in Machine LearningComputer Science
Anomaly Detection Techniques and ApplicationsComputer Science

Is this record sound?

suspect

Several fields of this record are missing or contradict each other. Treat its figures with suspicion — it is shown unaltered because correcting a source's record silently is worse than showing you the problem.

  • weakensThe source lists no authors for this work at all, so there is nobody to attribute it to and it appears on no author page.
  • weakensNo references are recorded despite 4,755 citations. A paper this heavily cited did not cite nothing, so the record is incomplete.
  • supportsThe DOI's year agrees with the publication year.
  • supportsA title is present.

Provenance

Everything above was read from one stored OpenAlex payload, fetched 2026-09-04T03:58:44+00:00.

sha256 648f8491aaceaa34…