LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition

Facial recognition systems are increasingly deployed by private corporations, government agencies, and contractors for consumer services and mass surveillance programs alike. These systems are typically built by scraping social media profiles for user images. Adversarial perturbations have been proposed for bypassing facial recognition systems. However, existing methods fail on full-scale systems and commercial APIs. We develop our own adversarial filter that accounts for the entire image processing pipeline and is demonstrably effective against industrial-grade pipelines that include face detection and large scale databases. Additionally, we release an easy-to-use webtool that significantly degrades the accuracy of Amazon Rekognition and the Microsoft Azure Face Recognition API, reducing the accuracy of each to below 1%.

[1]  Jonathon Shlens,et al.  Explaining and Harnessing Adversarial Examples , 2014, ICLR.

[2]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Yuxiao Hu,et al.  MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition , 2016, ECCV.

[4]  Ira Kemelmacher-Shlizerman,et al.  The MegaFace Benchmark: 1 Million Faces for Recognition at Scale , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[6]  Samy Bengio,et al.  Adversarial examples in the physical world , 2016, ICLR.

[7]  Bhiksha Raj,et al.  SphereFace: Deep Hypersphere Embedding for Face Recognition , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Carlos D. Castillo,et al.  UMDFaces: An annotated face dataset for training deep networks , 2016, 2017 IEEE International Joint Conference on Biometrics (IJCB).

[9]  David A. Wagner,et al.  Towards Evaluating the Robustness of Neural Networks , 2016, 2017 IEEE Symposium on Security and Privacy (SP).

[10]  White Guy.  Facial Recognition Is Accurate, if You’re a White Guy , 2018 .

[11]  Aleksander Madry,et al.  Towards Deep Learning Models Resistant to Adversarial Attacks , 2017, ICLR.

[12]  Xing Ji,et al.  CosFace: Large Margin Cosine Loss for Deep Face Recognition , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[13]  Alexei A. Efros,et al.  The Unreasonable Effectiveness of Deep Features as a Perceptual Metric , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[14]  Stefanos Zafeiriou,et al.  ArcFace: Additive Angular Margin Loss for Deep Face Recognition , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  L. Davis,et al.  Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectors , 2019, ECCV.

[16]  Kai Zhang,et al.  A Method for Curation of Web-Scraped Face Image Datasets , 2020, 2020 8th International Workshop on Biometrics and Forensics (IWBF).

[17]  Micah Goldblum,et al.  Adversarial attacks on machine learning systems for high-frequency trading , 2020, ICAIF.

[18]  Quanfu Fan,et al.  Adversarial T-Shirt! Evading Person Detectors in a Physical World , 2019, ECCV.

[19]  Ben Y. Zhao,et al.  Backdoor Attacks on Facial Recognition in the Physical World , 2020, ArXiv.

[20]  Ross B. Girshick,et al.  Focal Loss for Dense Object Detection , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Ben Y. Zhao,et al.  Fawkes: Protecting Privacy against Unauthorized Deep Learning Models , 2020, USENIX Security Symposium.

[22]  Jonas Geiping,et al.  Witchcraft: Efficient PGD Attacks with Random Step Size , 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[23]  Hang Su,et al.  Towards Privacy Protection by Generating Adversarial Identity Masks , 2020, ArXiv.

[24]  Tom Goldstein,et al.  Adversarial attacks on Copyright Detection Systems , 2019, ICML.

[25]  Sahil Singla,et al.  Perceptual Adversarial Robustness: Defense Against Unseen Threat Models , 2020, ICLR.

[26]  Weihong Deng,et al.  Towards Transferable Adversarial Attack Against Deep Face Recognition , 2020, IEEE Transactions on Information Forensics and Security.

[27]  Micah Goldblum,et al.  Technical Challenges for Training Fair Neural Networks , 2021, ArXiv.