Can we still avoid automatic face detection?

By Michael J. Wilber, Vitaly Shmatikov, Serge J. Belongie. 2016

58 citations recorded by the source corpus.

After decades of study, automatic face detection and recognition systems are now accurate and widespread. Naturally, this means users who wish to avoid automatic recognition are becoming less able to do so. Where do we stand in this cat-and-mouse race? We currently live in a society where everyone carries a camera in their pocket. Many people willfully upload most or all of the pictures they take to social networks which invest heavily in automatic face recognition systems. In this setting, is it still possible for privacy-conscientious users to avoid automatic face detection and recognition? If so, how? Must evasion techniques be obvious to be effective, or are there still simple measures that users can use to protect themselves? In this work, we find ways to evade face detection on Facebook, a representative example of a popular social network that uses automatic face detection to enhance their service. We challenge widely-held beliefs about evading face detection: do our old techniques such as blurring the face region or wearing "privacy glasses" still work? We show that in general, state-of-the-art detectors can often find faces even if the subject wears occluding clothing or even if the uploader damages the photo to prevent faces from being detected.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

Citations in the corpus

Defeating Image Obfuscation with Deep Learning (2016, background): “Wilber et al. [50] used Facebook’s face tagging system as a black-box tool to determine if faces ob-fuscated with various techniques, including blurring, are still recognizable by Facebook.”
Faceless Person Recognition: Privacy Implications in Social Media (2016, methodology): “We consider both black and white, since [47] showed that commercial systems might react differently to these.”
Towards Practical Verification of Machine Learning: The Case of Computer Vision Systems (2017, background): “Failing exhaustive input verification, an alternative approach is to take an existing input, alter it, and check or enhance the ML model on the altered input [8], [16], [23], [27], [30], [32], [33], [37], [41], [44], [46], [51].”
PsyPhy: A Psychophysics Driven Evaluation Framework for Visual Recognition (2016, background): “[36] systematically apply noise, blur, occlusion, compression, textures and warping effects over 2D scenes to assess face detection performance.”
When Machine Learning Meets Privacy (2020, background): “First, the process becomes automatic with high accuracy [67, 151, 168].”
Towards a Visual Privacy Advisor: Understanding and Predicting Privacy Risks in Images (2017, unknown): “Apart from detecting attributes, some works introduce new privacy challenges in vision such as adversarial perturbations [31, 35], privacy-preserving video capture [1, 36, 33, 37], person re-identification [2, 30], avoiding face detection [46, 16], full body re-identification [34] and privacy-sensit”
I Know That Person: Generative Full Body and Face De-identification of People in Images (2017, background): “Despite a growing body of evidence suggesting that a wealth of information can be mined from publicly available photos even if the faces of humans are blurred, pixelated or even completely covered with a black box [21, 33, 23], commercial providers and general public still tend to view these naive t”