# Can We Rely on AI?

arXiv: https://arxiv.org/abs/2308.15092 · HTML: https://mlsanity.com/paper/2308.15092/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 29 Aug 2023.

## Builds on (most cited first, 22 of 22)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [One pixel attack for fooling deep neural networks](https://mlsanity.com/paper/1710.08864/) (2017)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Are aligned neural networks adversarially aligned?](https://mlsanity.com/paper/2306.15447/) (2023)
- [Explanations can be manipulated and geometry is to blame](https://mlsanity.com/paper/1906.07983/) (2019)
- [On instabilities of deep learning in image reconstruction - Does AI come at a cost?](https://mlsanity.com/paper/1902.05300/) (2019)
- [Fundamental Limitations of Alignment in Large Language Models](https://mlsanity.com/paper/2304.11082/) (2023)
- [Are adversarial examples inevitable?](https://mlsanity.com/paper/1809.02104/) (2018)
- [Learning with a Strong Adversary](https://mlsanity.com/paper/1511.03034/) (2015)
- [DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flips](https://mlsanity.com/paper/2003.13746/) (2020)
- [Art of singular vectors and universal adversarial perturbations](https://mlsanity.com/paper/1709.03582/) (2017)
- [Subnet Replacement: Deployment-stage backdoor attack against deep neural networks in gray-box setting](https://mlsanity.com/paper/2107.07240/) (2021)
- [The mathematics of adversarial attacks in AI -- Why deep learning is unstable despite the existence of stable neural networks](https://mlsanity.com/paper/2109.06098/) (2021)
- [A LLM Assisted Exploitation of AI-Guardian](https://mlsanity.com/paper/2307.15008/) (2023)
- [On Adversarial Examples and Stealth Attacks in Artificial Intelligence Systems](https://mlsanity.com/paper/2004.04479/) (2020)
- [The Feasibility and Inevitability of Stealth Attacks](https://mlsanity.com/paper/2106.13997/) (2021)
- [Gamma-convergence of a nonlocal perimeter arising in adversarial machine learning](https://mlsanity.com/paper/2211.15223/) (2022)
- [Adversarial Ink: Componentwise Backward Error Attacks on Deep Learning](https://mlsanity.com/paper/2306.02918/) (2023)

## Abstract (arXiv)

Over the last decade, adversarial attack algorithms have revealed instabilities in deep learning tools. These algorithms raise issues regarding safety, reliability and interpretability in artificial intelligence; especially in high risk settings. From a practical perspective, there has been a war of escalation between those developing attack and defence strategies. At a more theoretical level, researchers have also studied bigger picture questions concerning the existence and computability of attacks. Here we give a brief overview of the topic, focusing on aspects that are likely to be of interest to researchers in applied and computational mathematics.