paper-with-me

홈 › Papers

Toward Face Biometric De-identification using Adversarial Examples

2023-02-07 · Mahdi Ghafourian, Julian Fierrez, Luis Felipe Gomez, Ruben Vera-Rodriguez, Aythami Morales, Zohra Rezgui, Raymond Veldhuis

The remarkable success of face recognition (FR) has endangered the privacy of internet users particularly in social media. Recently, researchers turned to use adversarial examples as a countermeasure. In this paper, we assess the effectiveness of using two widely known adversarial methods (BIM and ILLC) for de-identifying personal images. We discovered, unlike previous claims in the literature, that it is not easy to get a high protection success rate (suppressing identification rate) with imperceptible adversarial perturbation to the human visual system. Finally, we found out that the transferability of adversarial examples is highly affected by the training parameters of the network with which they are generated.

📄 PDF Abstract BibTeX arXiv:2302.03657

Code (0)

등록된 구현이 없습니다.

Tasks

De-identificationFace Recognition

Similar Papers 제목 키워드 기반

Siamese Generative Adversarial Privatizer for Biometric Data

2018-04-23 · Witold Oleszkiewicz, Peter Kairouz, Karol Piczak, Ram Rajagopal 외

State-of-the-art machine learning algorithms can be fooled by carefully crafted adversarial examples. As such, adversarial examples present a concrete problem in AI safety. In this work we turn the tables and ask the fol…

Emotion Recognition

Adversarial Attacks on Deep Learning Systems for User Identification based on Motion Sensors

2020-09-02 · Cezara Benegui, Radu Tudor Ionescu

For the time being, mobile devices employ implicit authentication mechanisms, namely, unlock patterns, PINs or biometric-based systems such as fingerprint or face recognition. While these systems are prone to well-known …

Face RecognitionUser Identification

Tubes Among Us: Analog Attack on Automatic Speaker Identification

2022-02-06 · Shimaa Ahmed, Yash Wani, Ali Shahin Shamsabadi, Mohammad Yaghini 외

Recent years have seen a surge in the popularity of acoustics-enabled personal devices powered by machine learning. Yet, machine learning has proven to be vulnerable to adversarial examples. A large number of modern syst…

BIG-bench Machine LearningSpeaker Identification

Ear2Face: Deep Biometric Modality Mapping

2020-06-02 · Dogucan Yaman, Fevziye Irem Eyiokur, Hazim Kemal Ekenel

In this paper, we explore the correlation between different visual biometric modalities. For this purpose, we present an end-to-end deep neural network model that learns a mapping between the biometric modalities. Namely…

Image-to-Image TranslationPerson Identification

Bridging Data Trials and Task Barriers: A Unified Framework for Sketch Biometric Identification

2026-05-17 · Decheng Liu, Bin Hu, Xinbo Gao, Dawei Zhou 외 arxiv

Different from existing cross-modality identification tasks (e.g., heterogeneous face recognition, sketch re-identification, etc.), we introduce a novel yet practical setting for these related identification tasks, named…

Heterogeneous Face RecognitionPerson Re-IdentificationContinual Learning