# On managing vulnerabilities in AI/ML systems

arXiv: https://arxiv.org/abs/2101.10865 · HTML: https://mlsanity.com/paper/2101.10865/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 62 references that are in the map.
- First posted on arXiv 22 Jan 2021.

## Builds on (most cited first, 14 of 14)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [An overview of gradient descent optimization algorithms](https://mlsanity.com/paper/1609.04747/) (2016)
- [On Adaptive Attacks to Adversarial Example Defenses](https://mlsanity.com/paper/2002.08347/) (2020)
- [On Evaluating Adversarial Robustness](https://mlsanity.com/paper/1902.06705/) (2019)
- [Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning](https://mlsanity.com/paper/1712.03141/) (2017)
- [Technical Report on the CleverHans v2.1.0 Adversarial Examples Library](https://mlsanity.com/paper/1610.00768/) (2016)
- [Adversarial Machine Learning -- Industry Perspectives](https://mlsanity.com/paper/2002.05646/) (2020)
- [Research Priorities for Robust and Beneficial Artificial Intelligence](https://mlsanity.com/paper/1602.03506/) (2016)
- [Cryptanalytic Extraction of Neural Network Models](https://mlsanity.com/paper/2003.04884/) (2020)
- [The Art, Science, and Engineering of Fuzzing: A Survey](https://mlsanity.com/paper/1812.00140/) (2018)
- [Failure Modes in Machine Learning Systems](https://mlsanity.com/paper/1911.11034/) (2019)
- [Law and Adversarial Machine Learning](https://mlsanity.com/paper/1810.10731/) (2018)

## Built on by (most cited first, 5 of 5)

- [Evaluating the Cybersecurity Risk of Real World, Machine Learning Production Systems](https://mlsanity.com/paper/2107.01806/) (2021)
- [A Survey on Offensive AI Within Cybersecurity](https://mlsanity.com/paper/2410.03566/) (2024)
- [Color Teams for Machine Learning Development](https://mlsanity.com/paper/2110.10601/) (2021)
- [Measuring AI Systems Beyond Accuracy](https://mlsanity.com/paper/2204.04211/) (2022)
- [On Security Weaknesses and Vulnerabilities in Deep Learning Systems](https://mlsanity.com/paper/2406.08688/) (2024)

## Abstract (arXiv)

This paper explores how the current paradigm of vulnerability management might adapt to include machine learning systems through a thought experiment: what if flaws in machine learning (ML) were assigned Common Vulnerabilities and Exposures (CVE) identifiers (CVE-IDs)? We consider both ML algorithms and model objects. The hypothetical scenario is structured around exploring the changes to the six areas of vulnerability management: discovery, report intake, analysis, coordination, disclosure, and response. While algorithm flaws are well-known in the academic research community, there is no apparent clear line of communication between this research community and the operational communities that deploy and manage systems that use ML. The thought experiments identify some ways in which CVE-IDs may establish some useful lines of communication between these two communities. In particular, it would start to introduce the research community to operational security concepts, which appears to be a gap left by existing efforts.