paper-with-me

Papers

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

2021-01-20 · ICLR 2021 1 · Valeriia Cherepanova, Micah Goldblum, Harrison Foley, Shiyuan Duan, John Dickerson, Gavin Taylor, Tom Goldstein

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%.

📄 PDF Abstract BibTeX arXiv:2101.07922

Code (0)

등록된 구현이 없습니다.

Tasks

Face DetectionFace Recognition

Similar Papers 제목 키워드 기반

Adversary for Social Good: Leveraging Adversarial Attacks to Protect Personal Attribute Privacy

2023-06-04 · Xiaoting Li, Lingwei Chen, Dinghao Wu

Social media has drastically reshaped the world that allows billions of people to engage in such interactive environments to conveniently create and share content with the public. Among them, text data (e.g., tweets, blo…

Adversarial AttackAttribute

Data Poisoning Won’t Save You From Facial Recognition

2021-06-18 · ICML Workshop AML 2021 7 · Evani Radiya-Dixit, Florian Tramer

Data poisoning has been proposed as a compelling defense against facial recognition models trained on Web-scraped pictures. By perturbing the images they post online, users can fool models into misclassifying future (unp…

Data Poisoning

Targeted Attack Improves Protection against Unauthorized Diffusion Customization

2023-10-07 · BoYang Zheng, Chumeng Liang, Xiaoyu Wu

Diffusion models build a new milestone for image generation yet raising public concerns, for they can be fine-tuned on unauthorized images for customization. Protection based on adversarial attacks rises to encounter thi…

Adversarial AttackImage GenerationMisinformation

Data Poisoning Won't Save You From Facial Recognition

2021-06-28 · Evani Radiya-Dixit, Sanghyun Hong, Nicholas Carlini, Florian Tramèr

Data poisoning has been proposed as a compelling defense against facial recognition models trained on Web-scraped pictures. Users can perturb images they post online, so that models will misclassify future (unperturbed) …

Data Poisoning

Adversarial machine learning for protecting against online manipulation

2021-11-23 · Stefano Cresci, Marinella Petrocchi, Angelo Spognardi, Stefano Tognazzi

Adversarial examples are inputs to a machine learning system that result in an incorrect output from that system. Attacks launched through this type of input can cause severe consequences: for example, in the field of im…

BIG-bench Machine Learning