# Security and Safety Aspects of AI in Industry Applications

arXiv: https://arxiv.org/abs/2207.10809 · HTML: https://mlsanity.com/paper/2207.10809/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 33 references that are in the map.
- First posted on arXiv 16 Jul 2022.

## Builds on (most cited first, 13 of 13)

- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [Understanding Deep Networks via Extremal Perturbations and Smooth Masks](https://mlsanity.com/paper/1910.08485/) (2019)
- [Dataset Security for Machine Learning: Data Poisoning, Backdoor Attacks, and Defenses](https://mlsanity.com/paper/2012.10544/) (2020)
- [Improving the Robustness of Deep Neural Networks via Stability Training](https://mlsanity.com/paper/1604.04326/) (2016)
- [Conscientious Classification: A Data Scientist's Guide to Discrimination-Aware Classification](https://mlsanity.com/paper/1907.09013/) (2019)
- [Holistic Adversarial Robustness of Deep Learning Models](https://mlsanity.com/paper/2202.07201/) (2022)
- [RTGPU: Real-Time GPU Scheduling of Hard Deadline Parallel Tasks with Fine-Grain Utilization](https://mlsanity.com/paper/2101.10463/) (2021)
- [A Survey of Techniques for Improving Security of GPUs](https://mlsanity.com/paper/1804.00114/) (2018)
- [Dynamic Lockstep Processors for Applications with Functional Safety Relevance](https://mlsanity.com/paper/2107.08997/) (2021)
- [Designing Neural Networks for Real-Time Systems](https://mlsanity.com/paper/2008.11830/) (2020)
- [Dependable Neural Networks Through Redundancy, A Comparison of Redundant Architectures](https://mlsanity.com/paper/2108.02565/) (2021)

## Abstract (arXiv)

In this relatively informal discussion-paper we summarise issues in the domains of safety and security in machine learning that will affect industry sectors in the next five to ten years. Various products using neural network classification, most often in vision related applications but also in predictive maintenance, have been researched and applied in real-world applications in recent years. Nevertheless, reports of underlying problems in both safety and security related domains, for instance adversarial attacks have unsettled early adopters and are threatening to hinder wider scale adoption of this technology. The problem for real-world applicability lies in being able to assess the risk of applying these technologies. In this discussion-paper we describe the process of arriving at a machine-learnt neural network classifier pointing out safety and security vulnerabilities in that workflow, citing relevant research where appropriate.