# Examining the Human Perceptibility of Black-Box Adversarial Attacks on Face Recognition

arXiv: https://arxiv.org/abs/2107.09126 · HTML: https://mlsanity.com/paper/2107.09126/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 20 references that are in the map.
- First posted on arXiv 19 Jul 2021.

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

- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [VGGFace2: A dataset for recognising faces across pose and age](https://mlsanity.com/paper/1710.08092/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Square Attack: a query-efficient black-box adversarial attack via random search](https://mlsanity.com/paper/1912.00049/) (2019)
- [Black-box Adversarial Attacks with Limited Queries and Information](https://mlsanity.com/paper/1804.08598/) (2018)
- [Simple Black-box Adversarial Attacks](https://mlsanity.com/paper/1905.07121/) (2019)
- [Efficient Decision-based Black-box Adversarial Attacks on Face Recognition](https://mlsanity.com/paper/1904.04433/) (2019)
- [Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors](https://mlsanity.com/paper/1807.07978/) (2018)
- [Perceptual Adversarial Robustness: Defense Against Unseen Threat Models](https://mlsanity.com/paper/2006.12655/) (2020)
- [On the Suitability of Lp-norms for Creating and Preventing Adversarial Examples](https://mlsanity.com/paper/1802.09653/) (2018)
- [Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Network](https://mlsanity.com/paper/1811.12026/) (2018)
- [Unravelling Robustness of Deep Learning based Face Recognition Against Adversarial Attacks](https://mlsanity.com/paper/1803.00401/) (2018)
- [Should Adversarial Attacks Use Pixel p-Norm?](https://mlsanity.com/paper/1906.02439/) (2019)

## Abstract (arXiv)

The modern open internet contains billions of public images of human faces across the web, especially on social media websites used by half the world's population. In this context, Face Recognition (FR) systems have the potential to match faces to specific names and identities, creating glaring privacy concerns. Adversarial attacks are a promising way to grant users privacy from FR systems by disrupting their capability to recognize faces. Yet, such attacks can be perceptible to human observers, especially under the more challenging black-box threat model. In the literature, the justification for the imperceptibility of such attacks hinges on bounding metrics such as ℓp norms. However, there is not much research on how these norms match up with human perception. Through examining and measuring both the effectiveness of recent black-box attacks in the face recognition setting and their corresponding human perceptibility through survey data, we demonstrate the trade-offs in perceptibility that occur as attacks become more aggressive. We also show how the ℓ2 norm and other metrics do not correlate with human perceptibility in a linear fashion, thus making these norms suboptimal at measuring adversarial attack perceptibility.