12,444 Hits in 6.3 sec

Simulated Adversarial Testing of Face Recognition Models [article]

Nataniel Ruiz, Adam Kortylewski, Weichao Qiu, Cihang Xie, Sarah Adel Bargal, Alan Yuille, Stan Sclaroff
2022 arXiv   pre-print
Using our proposed method, we can find adversarial synthetic faces that fool contemporary face recognition models.  ...  We apply this method in a face recognition setup. We show that certain weaknesses of models trained on real data can be discovered using simulated samples.  ...  Simulated Adversarial Testing of Face Recognition Models In this section we evaluate adversarial testing of face recognition models for face verification.  ... 
arXiv:2106.04569v3 fatcat:727wh7gebzed5cy6nljdyw5i6y

Controllable Evaluation and Generation of Physical Adversarial Patch on Face Recognition [article]

Xiao Yang, Yinpeng Dong, Tianyu Pang, Zihao Xiao, Hang Su, Jun Zhu
2022 arXiv   pre-print
Recent studies have revealed the vulnerability of face recognition models against physical adversarial patches, which raises security concerns about the deployed face recognition systems.  ...  white-box and black-box face recognition models.  ...  ] that is a state-of-the-art transferable adversarial method on face recognition based on generative models.  ... 
arXiv:2203.04623v2 fatcat:53fouax7kvhwnkilhx27ihc54y

Robust Physical-World Attacks on Face Recognition [article]

Xin Zheng, Yanbo Fan, Baoyuan Wu, Yong Zhang, Jue Wang, Shirui Pan
2021 arXiv   pre-print
However, recent studies have shown that DNNs are very vulnerable to adversarial examples, raising serious concerns on the security of real-world face recognition.  ...  Finally, we construct a standardized testing protocol to facilitate the fair evaluation of physical attacks on face recognition, and extensive experiments on both dodging and impersonation attacks demonstrate  ...  Finally, we build a standardized testing protocol for physical attacks on face recognition and conduct a comprehensive experimental study on the adversarial robustness of state-of-the-art face recognition  ... 
arXiv:2109.09320v1 fatcat:fu3s3vqwdvfz7bhdt2ixpxvgza

Adversarial Learning with Margin-based Triplet Embedding Regularization [article]

Yaoyao Zhong, Weihong Deng
2019 arXiv   pre-print
classification and deep face recognition.  ...  that the obtained model learns to resist adversarial examples.  ...  This work was partially supported by the National Natural Science Foundation of China under Grant Nos. 61573068 and 61871052.  ... 
arXiv:1909.09481v1 fatcat:tc2ttjpbcbgq7dsgex25lhvqz4

PrivHAR: Recognizing Human Actions From Privacy-preserving Lens [article]

Carlos Hinojosa, Miguel Marquez, Henry Arguello, Ehsan Adeli, Li Fei-Fei, Juan Carlos Niebles
2022 arXiv   pre-print
Our framework parameterizes the camera lens to successfully degrade the quality of the videos to inhibit privacy attributes and protect against adversarial attacks while maintaining relevant features for  ...  The accelerated use of digital cameras prompts an increasing concern about privacy and security, particularly in applications such as action recognition.  ...  Specifically, we use an implementation of the face recognition network ArcFace [11] , train on Microsoft Celeb (MS-Celeb-1M) [15] and test on LFW [19] datasets. Qualitative Results.  ... 
arXiv:2206.03891v1 fatcat:jawwl7qxhjfc5aa3pzcfbilhta

Evaluation of Momentum Diverse Input Iterative Fast Gradient Sign Method (M-DI2-FGSM) Based Attack Method on MCS 2018 Adversarial Attacks on Black Box Face Recognition System [article]

Md Ashraful Alam Milton
2018 arXiv   pre-print
We tested our method on MCS 2018 Adversarial Attacks on Black Box Face Recognition challenge and found competitive result.  ...  In this regard, MCS 2018 Adversarial Attacks on Black Box Face Recognition challenge aims to facilitate the research of finding new adversarial attack techniques and their effectiveness in generating adversarial  ...  This could elicit a great opportunity to test the face recognition system against this robust adversarial attack and pave the way to take measures against adversarial attack.  ... 
arXiv:1806.08970v1 fatcat:mfwxmgl7nraijfiva5ngdeegia

3D-Aided Deep Pose-Invariant Face Recognition

Jian Zhao, Lin Xiong, Yu Cheng, Yi Cheng, Jianshu Li, Li Zhou, Yan Xu, Jayashree Karlekar, Sugiri Pranata, Shengmei Shen, Junliang Xing, Shuicheng Yan (+1 others)
2018 Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence  
To mitigate this gap, we propose a 3D-Aided Deep Pose-Invariant Face Recognition Model (3D-PIM), which automatically recovers realistic frontal faces from arbitrary poses through a 3D face model in a novel  ...  Specifically, 3D-PIM incorporates a simulator with the aid of a 3D Morphable Model (3D MM) to obtain shape and appearance prior for accelerating face normalization learning, requiring less training data  ...  The work of Junliang Xing was partially supported by the National Science Foundation of Chian 61672519.  ... 
doi:10.24963/ijcai.2018/165 dblp:conf/ijcai/ZhaoXCCLZXKPSXY18 fatcat:2bfsdg742veahofrzjsped5zje

Robust face recognition: How much face Is needed?

Bunzel Niklas
2022 IS&T International Symposium on Electronic Imaging Science and Technology  
We have identified three inconspicuous facial areas to wear adversarial examples to attack face recognition. These are the mouth-nose section, the forehead and the eye area.  ...  Face recognition systems are used in high security applications for identification, authentication and authorization.  ...  support of the National Research Center for Applied Cybersecurity ATHENE.  ... 
doi:10.2352/ei.2022.34.4.mwsf-209 fatcat:rtdh2dyv3ngcvcfgwm656cedfi

Using Photorealistic Face Synthesis and Domain Adaptation to Improve Facial Expression Analysis [article]

Behzad Bozorgtabar, Mohammad Saeed Rad, Hazim Kemal Ekenel and Jean-Philippe Thiran
2019 arXiv   pre-print
Cross-domain synthesizing realistic faces to learn deep models has attracted increasing attention for facial expression analysis as it helps to improve the performance of expression recognition accuracy  ...  We demonstrate that the expression recognition performance can be enhanced by benefiting from our face synthesis model.  ...  In particular, we utilize a 3D Morphable Model using bilinear face model [34] to construct a simulated frontal face image. Fig. 3 shows examples of simulated faces.  ... 
arXiv:1905.08090v1 fatcat:ehsfrdnq4bcmxk5fd25ilm5ysq

Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition Models [article]

Alon Zolfi and Shai Avidan and Yuval Elovici and Asaf Shabtai
2022 arXiv   pre-print
Deep learning-based facial recognition (FR) models have demonstrated state-of-the-art performance in the past few years, even when wearing protective medical face masks became commonplace during the COVID  ...  In this paper, we propose Adversarial Mask, a physical universal adversarial perturbation (UAP) against state-of-the-art FR models that is applied on face masks in the form of a carefully crafted pattern  ...  The widespread adoption of face masks and the ever-increasing use of deep learningbased facial recognition (FR) models in everyday systems can be leveraged to perpetrate targeted adversarial attacks that  ... 
arXiv:2111.10759v2 fatcat:ajbtiikr6jhhpectn4yluk54wu

Image Reconstruction of Ghost Imaging Based on Improved Generative Adversarial Networks

Xu Chen
2022 Journal of Applied Mathematics and Physics  
In this paper, we improve traditional generative adversarial networks (GAN) with reference to residual networks and convolutional neural networks to facilitate the reconstruction of complex objects that  ...  ) of completely different complexity than the training set.  ...  Simulation Results In our work, in order to verify the generalization ability of the network, the face dataset is used as the test data of the network, which is selected from the open-source CelebA-Cropped  ... 
doi:10.4236/jamp.2022.104076 fatcat:mc7osyhsa5gsbfrvt5zvxmflyy

Enhance Gender and Identity Preservation in Face Aging Simulation for Infants and Toddlers [article]

Yao Xiao, Yijun Zhao
2020 arXiv   pre-print
We trained our model using the publicly available UTKFace dataset and evaluated our model by simulating up to 100 years of aging on 1,156 male and 1,207 female infant and toddler face photos.  ...  In recent years, deep learning-based approaches have made remarkable progress in modeling the aging process of the human face.  ...  For each test photo, we display a simulation block of three rows, each of which consists of predicted faces by the indicated model for the 0-5, 16-20, 31-40, 51-60, and >70 age buckets.  ... 
arXiv:2011.07431v1 fatcat:i2fgrqpu45dpfpivdqtwc7aig4

Beyond Digital Domain: Fooling Deep Learning Based Recognition System in Physical World

Kaichen Yang, Tzungyu Tsai, Honggang Yu, Tsung-Yi Ho, Yier Jin
The problem of attacking object detection models and adversarial attacks in physical world are rarely touched.  ...  We also test our attack in a variety of commercial platforms for object detection and demonstrate that our attack is still valid on these platforms.  ...  Through testing our recorded video we wish to know the reaction of the traditional non-DNN based detection algorithms facing physical adversarial objects generated from DNN based models.  ... 
doi:10.1609/aaai.v34i01.5459 fatcat:d3cw2pj4ajfolkbtttq5pzbn5q

Dual-Agent GANs for Photorealistic and Identity Preserving Profile Face Synthesis

Jian Zhao, Lin Xiong, Jayashree Karlekar, Jianshu Li, Fang Zhao, Zhecan Wang, Sugiri Pranata, Shengmei Shen, Shuicheng Yan, Jiashi Feng
2017 Neural Information Processing Systems  
In particular, we employ an off-the-shelf 3D face model as a simulator to generate profile face images with varying poses.  ...  To narrow this gap, we propose a Dual-Agent Generative Adversarial Network (DA-GAN) model, which can improve the realism of a face simulator's output using unlabeled real faces, while preserving the identity  ...  The IJB-A benchmark dataset, relevant information and leaderboard can be found at  ... 
dblp:conf/nips/ZhaoXKLZWPSYF17 fatcat:lpom7puvuzee3gpyfu6c6bxz3u

Towards Transferable Adversarial Attack against Deep Face Recognition [article]

Yaoyao Zhong, Weihong Deng
2020 arXiv   pre-print
In this work, we first investigate the characteristics of transferable adversarial attacks in face recognition by showing the superiority of feature-level methods over label-level methods.  ...  Face recognition has achieved great success in the last five years due to the development of deep learning methods.  ...  remained to be done on transferable adversarial attacks in deep face recognition because of the particularity of deep face models.  ... 
arXiv:2004.05790v1 fatcat:yokl5sgyzfdtpirp72tn76sus4
« Previous Showing results 1 — 15 out of 12,444 results