Investigating the Impact of Inclusion in Face Recognition Training Data
on Individual Face Identification
- URL: http://arxiv.org/abs/2001.03071v2
- Date: Fri, 10 Jan 2020 21:17:59 GMT
- Title: Investigating the Impact of Inclusion in Face Recognition Training Data
on Individual Face Identification
- Authors: Chris Dulhanty, Alexander Wong
- Abstract summary: We audit ArcFace, a state-of-the-art, open source face recognition system, in a large-scale face identification experiment with more than one million distractor images.
We find a Rank-1 face identification accuracy of 79.71% for individuals present in the model's training data and an accuracy of 75.73% for those not present.
- Score: 93.5538147928669
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Modern face recognition systems leverage datasets containing images of
hundreds of thousands of specific individuals' faces to train deep
convolutional neural networks to learn an embedding space that maps an
arbitrary individual's face to a vector representation of their identity. The
performance of a face recognition system in face verification (1:1) and face
identification (1:N) tasks is directly related to the ability of an embedding
space to discriminate between identities. Recently, there has been significant
public scrutiny into the source and privacy implications of large-scale face
recognition training datasets such as MS-Celeb-1M and MegaFace, as many people
are uncomfortable with their face being used to train dual-use technologies
that can enable mass surveillance. However, the impact of an individual's
inclusion in training data on a derived system's ability to recognize them has
not previously been studied. In this work, we audit ArcFace, a
state-of-the-art, open source face recognition system, in a large-scale face
identification experiment with more than one million distractor images. We find
a Rank-1 face identification accuracy of 79.71% for individuals present in the
model's training data and an accuracy of 75.73% for those not present. This
modest difference in accuracy demonstrates that face recognition systems using
deep learning work better for individuals they are trained on, which has
serious privacy implications when one considers all major open source face
recognition training datasets do not obtain informed consent from individuals
during their collection.
Related papers
- LAFS: Landmark-based Facial Self-supervised Learning for Face
Recognition [37.4550614524874]
We focus on learning facial representations that can be adapted to train effective face recognition models.
We explore the learning strategy of unlabeled facial images through self-supervised pretraining.
Our method achieves significant improvement over the state-of-the-art on multiple face recognition benchmarks.
arXiv Detail & Related papers (2024-03-13T01:07:55Z) - Privacy-Preserving Face Recognition in Hybrid Frequency-Color Domain [16.05230409730324]
Face image is a sensitive biometric attribute tied to the identity information of each user.
This paper proposes a hybrid frequency-color fusion approach to reduce the input dimensionality of face recognition.
It has around 2.6% to 4.2% higher accuracy than the state-of-the-art in the 1:N verification scenario.
arXiv Detail & Related papers (2024-01-24T11:27:32Z) - Diff-Privacy: Diffusion-based Face Privacy Protection [58.1021066224765]
In this paper, we propose a novel face privacy protection method based on diffusion models, dubbed Diff-Privacy.
Specifically, we train our proposed multi-scale image inversion module (MSI) to obtain a set of SDM format conditional embeddings of the original image.
Based on the conditional embeddings, we design corresponding embedding scheduling strategies and construct different energy functions during the denoising process to achieve anonymization and visual identity information hiding.
arXiv Detail & Related papers (2023-09-11T09:26:07Z) - Privacy-Preserving Face Recognition Using Random Frequency Components [46.95003101593304]
Face recognition has sparked increasing privacy concerns.
We propose to conceal visual information by pruning human-perceivable low-frequency components.
We distill our findings into a novel privacy-preserving face recognition method, PartialFace.
arXiv Detail & Related papers (2023-08-21T04:31:02Z) - Privacy-Preserving Face Recognition with Learnable Privacy Budgets in
Frequency Domain [77.8858706250075]
This paper proposes a privacy-preserving face recognition method using differential privacy in the frequency domain.
Our method performs very well with several classical face recognition test sets.
arXiv Detail & Related papers (2022-07-15T07:15:36Z) - An Attack on Feature Level-based Facial Soft-biometric Privacy
Enhancement [13.780253190395715]
We introduce an attack on feature level-based facial soft-biometric privacy-enhancement techniques.
It is able to circumvent the privacy enhancement to a considerable degree and is able to correctly classify gender with an accuracy of up to approximately 90%.
arXiv Detail & Related papers (2021-11-24T10:41:15Z) - FedFace: Collaborative Learning of Face Recognition Model [66.84737075622421]
FedFace is a framework for collaborative learning of face recognition models.
It learns an accurate and generalizable face recognition model where the face images stored at each client are neither shared with other clients nor the central host.
Our code and pre-trained models will be publicly available.
arXiv Detail & Related papers (2021-04-07T09:25:32Z) - Facial Expressions as a Vulnerability in Face Recognition [73.85525896663371]
This work explores facial expression bias as a security vulnerability of face recognition systems.
We present a comprehensive analysis of how facial expression bias impacts the performance of face recognition technologies.
arXiv Detail & Related papers (2020-11-17T18:12:41Z) - Real Time Face Recognition Using Convoluted Neural Networks [0.0]
Convolutional Neural Networks are proved to be best for facial recognition.
The creation of dataset is done by converting face videos of the persons to be recognized into hundreds of images of person.
arXiv Detail & Related papers (2020-10-09T12:04:49Z) - Towards Face Encryption by Generating Adversarial Identity Masks [53.82211571716117]
We propose a targeted identity-protection iterative method (TIP-IM) to generate adversarial identity masks.
TIP-IM provides 95%+ protection success rate against various state-of-the-art face recognition models.
arXiv Detail & Related papers (2020-03-15T12:45:10Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.