RECORD
Robust Ensemble Morph Detection with Domain Generalization
Computer Vision and Pattern Recognition · Submitted 16 Sep 2022
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim In addition, we validate that our robust ensemble model gain better robustness against several adversarial attacks while outperforming the state-of-the-art studies.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Although a substantial amount of studies is dedicated to morph detection, most of them fail to generalize for morph faces outside of their training paradigm. Moreover, recent morph detection methods are highly vulnerable to adversarial attacks. In this paper, we intend to learn a morph detection model with high generalization to a wide range of morphing attacks and high robustness against different adversarial attacks. To this aim, we develop an ensemble of convolutional neural networks (CNNs) and Transformer models to benefit from their capabilities simultaneously. To improve the robust accuracy of the ensemble model, we employ multi-perturbation adversarial training and generate adversarial examples with high transferability for several single models. Our exhaustive evaluations demonstrate that the proposed robust ensemble model generalizes to several morphing attacks and face datasets. In addition, we validate that our robust ensemble model gain better robustness against several adversarial attacks while outperforming the state-of-the-art studies.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Although a substantial amount of studies is dedicated to morph detection, most of them fail to generalize for morph faces outside of their training paradigm. | gap 0.53 | 0.05 | 0.02 | asserted 1.00 |
| s1 | Moreover, recent morph detection methods are highly vulnerable to adversarial attacks. | background 0.70 | 0.06 | 0.02 | asserted 1.00 |
| s2 | In this paper, we intend to learn a morph detection model with high generalization to a wide range of morphing attacks and high robustness against different adversarial attacks. | contribution 0.88 | 0.24 | 0.08 | asserted 0.43 |
| s3 | To this aim, we develop an ensemble of convolutional neural networks (CNNs) and Transformer models to benefit from their capabilities simultaneously. | method 0.95 | 0.93 | 0.03 | asserted 0.95 |
| s4 | To improve the robust accuracy of the ensemble model, we employ multi-perturbation adversarial training and generate adversarial examples with high transferability for several single models. | method 0.99 | 0.94 | 0.03 | asserted 0.98 |
| s5 | Our exhaustive evaluations demonstrate that the proposed robust ensemble model generalizes to several morphing attacks and face datasets. | result 1.00 | 0.97 | 0.41 | asserted 1.00 |
| s6 | In addition, we validate that our robust ensemble model gain better robustness against several adversarial attacks while outperforming the state-of-the-art studies. | result 1.00 | 0.95 | 0.56 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Although a substantial amount of studies is dedicated to morph detection, most of them fail to generalize for morph faces outside of their training paradigm. Moreover, recent morph detection methods are highly vulnerable to adversarial attacks. In this paper, we intend to learn a morph detection model with high generalization to a wide range of morphing attacks and high robustness against different adversarial attacks. To this aim, we develop an ensemble of convolutional neural networks (CNNs) and Transformer models to benefit from their capabilities simultaneously. To improve the robust accuracy of the ensemble model, we employ multi-perturbation adversarial training and generate adversarial examples with high transferability for several single models. Our exhaustive evaluations demonstrate that the proposed robust ensemble model generalizes to several morphing attacks and face datasets. In addition, we validate that our robust ensemble model gain better robustness against several adversarial attacks while outperforming the state-of-the-art studies.
Human review
How the literature uses it
2 arXiv papers cite this in 2 sentences
Papers citing it · 1 sentence without a confident label
Cites it as background 1 paper
-
The Softmax training criterion can be formulated as follows [ref] : [equation] where $W_j ∈ℝ^d$ is $j$-th classifier (center), $d$ is the feature dimension, and $b_j$ is the bias for $j$-th Softmax output. $x_i$ is the learned representation of $i$-th sample, and $y_i$ is its corresponding ground truth. $N$ and $C$ represent the mini-batch size and the total number of classes, respectively.
A Quality Aware Sample-to-Sample Comparison for Face Recognition · Preliminaries · 0.83
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.