# Security and Machine Learning in the Real World

arXiv: https://arxiv.org/abs/2007.07205 · HTML: https://mlsanity.com/paper/2007.07205/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2020.

## Built on by (most cited first, 9 of 9)

- [Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection](https://mlsanity.com/paper/2110.14019/) (2021)
- [Towards more Practical Threat Models in Artificial Intelligence Security](https://mlsanity.com/paper/2311.09994/) (2023)
- [Particip-AI: A Democratic Surveying Framework for Anticipating Future AI Use Cases, Harms and Benefits](https://mlsanity.com/paper/2403.14791/) (2024)
- [Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems](https://mlsanity.com/paper/2104.08690/) (2021)
- [Adversarial Scratches: Deployable Attacks to CNN Classifiers](https://mlsanity.com/paper/2204.09397/) (2022)
- [Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries](https://mlsanity.com/paper/2104.08382/) (2021)
- [On the Exploitability of Audio Machine Learning Pipelines to Surreptitious Adversarial Examples](https://mlsanity.com/paper/2108.02010/) (2021)
- [Mental Models of Adversarial Machine Learning](https://mlsanity.com/paper/2105.03726/) (2021)
- [On Security Weaknesses and Vulnerabilities in Deep Learning Systems](https://mlsanity.com/paper/2406.08688/) (2024)

## Abstract (arXiv)

Machine learning (ML) models deployed in many safety- and business-critical systems are vulnerable to exploitation through adversarial examples. A large body of academic research has thoroughly explored the causes of these blind spots, developed sophisticated algorithms for finding them, and proposed a few promising defenses. A vast majority of these works, however, study standalone neural network models. In this work, we build on our experience evaluating the security of a machine learning software product deployed on a large scale to broaden the conversation to include a systems security view of these vulnerabilities. We describe novel challenges to implementing systems security best practices in software with ML components. In addition, we propose a list of short-term mitigation suggestions that practitioners deploying machine learning modules can use to secure their systems. Finally, we outline directions for new research into machine learning attacks and defenses that can serve to advance the state of ML systems security.