# Adversarial AI in Insurance: Pervasiveness and Resilience

arXiv: https://arxiv.org/abs/2301.07520 · HTML: https://mlsanity.com/paper/2301.07520/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 34 references that are in the map.
- First posted on arXiv 17 Jan 2023.

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

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Audio Adversarial Examples: Targeted Attacks on Speech-to-Text](https://mlsanity.com/paper/1801.01944/) (2018)
- [Adversarial Attacks and Defenses in Images, Graphs and Text: A Review](https://mlsanity.com/paper/1909.08072/) (2019)
- [Robust Physical-World Attacks on Deep Learning Models](https://mlsanity.com/paper/1707.08945/) (2017)
- [Adversarial Attacks Against Medical Deep Learning Systems](https://mlsanity.com/paper/1804.05296/) (2018)
- [A Survey On Universal Adversarial Attack](https://mlsanity.com/paper/2103.01498/) (2021)
- [Adversarial Attack Vulnerability of Medical Image Analysis Systems: Unexplored Factors](https://mlsanity.com/paper/2006.06356/) (2020)
- [Discrete Adversarial Attacks and Submodular Optimization with Applications to Text Classification](https://mlsanity.com/paper/1812.00151/) (2018)
- [Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge](https://mlsanity.com/paper/2007.15610/) (2020)

## Built on by (most cited first, 1 of 1)

- [LLMs and Agentic AI in Insurance Decision-Making: Opportunities and Challenges For Africa](https://mlsanity.com/paper/2508.15110/) (2025)

## Abstract (arXiv)

The rapid and dynamic pace of Artificial Intelligence (AI) and Machine Learning (ML) is revolutionizing the insurance sector. AI offers significant, very much welcome advantages to insurance companies, and is fundamental to their customer-centricity strategy. It also poses challenges, in the project and implementation phase. Among those, we study Adversarial Attacks, which consist of the creation of modified input data to deceive an AI system and produce false outputs. We provide examples of attacks on insurance AI applications, categorize them, and argue on defence methods and precautionary systems, considering that they can involve few-shot and zero-shot multilabelling. A related topic, with growing interest, is the validation and verification of systems incorporating AI and ML components. These topics are discussed in various sections of this paper.