# Adversarial Examples: Generation Proposal in the Context of Facial Recognition Systems

arXiv: https://arxiv.org/abs/2404.17760 · HTML: https://mlsanity.com/paper/2404.17760/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 10 references that are in the map.
- First posted on arXiv 27 Apr 2024.

## Builds on (most cited first, 6 of 6)

- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [Constructing Unrestricted Adversarial Examples with Generative Models](https://mlsanity.com/paper/1805.07894/) (2018)
- [On adversarial patches: real-world attack on ArcFace-100 face recognition system](https://mlsanity.com/paper/1910.07067/) (2019)
- [PuVAE: A Variational Autoencoder to Purify Adversarial Examples](https://mlsanity.com/paper/1903.00585/) (2019)

## Abstract (arXiv)

In this paper we investigate the vulnerability that facial recognition systems present to adversarial examples by introducing a new methodology from the attacker perspective. The technique is based on the use of the autoencoder latent space, organized with principal component analysis. We intend to analyze the potential to craft adversarial examples suitable for both dodging and impersonation attacks, against state-of-the-art systems. Our initial hypothesis, which was not strongly favoured by the results, stated that it would be possible to separate between the "identity" and "facial expression" features to produce high-quality examples. Despite the findings not supporting it, the results sparked insights into adversarial examples generation and opened new research avenues in the area.