# AI Product Security: A Primer for Developers

arXiv: https://arxiv.org/abs/2304.11087 · HTML: https://mlsanity.com/paper/2304.11087/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 18 Apr 2023.

## Builds on (most cited first, 9 of 9)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks](https://mlsanity.com/paper/1511.04508/) (2015)
- [Adversarial Examples: Attacks and Defenses for Deep Learning](https://mlsanity.com/paper/1712.07107/) (2017)
- [High Accuracy and High Fidelity Extraction of Neural Networks](https://mlsanity.com/paper/1909.01838/) (2019)
- [Adversarial Reprogramming of Neural Networks](https://mlsanity.com/paper/1806.11146/) (2018)
- [Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources](https://mlsanity.com/paper/2007.08714/) (2020)
- [Privacy and Trust Redefined in Federated Machine Learning](https://mlsanity.com/paper/2103.15753/) (2021)

## Abstract (arXiv)

Not too long ago, AI security used to mean the research and practice of how AI can empower cybersecurity, that is, AI for security. Ever since Ian Goodfellow and his team popularized adversarial attacks on machine learning, security for AI became an important concern and also part of AI security. It is imperative to understand the threats to machine learning products and avoid common pitfalls in AI product development. This article is addressed to developers, designers, managers and researchers of AI software products.