Clip2protect: Protecting facial privacy using text-guided makeup via adversarial latent search

F Shamshad, M Naseer… - Proceedings of the …, 2023 - openaccess.thecvf.com
The success of deep learning based face recognition systems has given rise to serious
privacy concerns due to their ability to enable unauthorized tracking of users in the digital …

Differentially private imaging via latent space manipulation

T Li, C Clifton - arXiv preprint arXiv:2103.05472, 2021 - arxiv.org
There is growing concern about image privacy due to the popularity of social media and
photo devices, along with increasing use of face recognition systems. However, established …

On generating identifiable virtual faces

Z Yuan, Z You, S Li, Z Qian, X Zhang… - Proceedings of the 30th …, 2022 - dl.acm.org
Face anonymization with generative models have become increasingly prevalent since they
sanitize private information by generating virtual face images, ensuring both privacy and …

Sok: Anti-facial recognition technology

E Wenger, S Shan, H Zheng… - 2023 IEEE Symposium …, 2023 - ieeexplore.ieee.org
The rapid adoption of facial recognition (FR) technology by both government and
commercial entities in recent years has raised concerns about civil liberties and privacy. In …

Obfuscation algorithm for privacy-preserving deep learning-based medical image analysis

AB Popescu, IA Taca, A Vizitiu, CI Nita, C Suciu… - Applied Sciences, 2022 - mdpi.com
Deep learning (DL)-based algorithms have demonstrated remarkable results in potentially
improving the performance and the efficiency of healthcare applications. Since the data …

Face De-identification: State-of-the-art Methods and Comparative Studies

J Cao, X Chen, B Liu, M Ding, R Xie, L Song… - arXiv preprint arXiv …, 2024 - arxiv.org
The widespread use of image acquisition technologies, along with advances in facial
recognition, has raised serious privacy concerns. Face de-identification usually refers to the …

Synthetic dataset generation for privacy-preserving machine learning

E Soufleri, G Saha, K Roy - arXiv preprint arXiv:2210.03205, 2022 - arxiv.org
Machine Learning (ML) has achieved enormous success in solving a variety of problems in
computer vision, speech recognition, object detection, to name a few. The principal reason …

Advanced techniques for preventing thermal imaging attacks

N Alotaibi, MS Islam, K Marky, M Khamis - Companion Proceedings of …, 2022 - dl.acm.org
Thermal cameras can be used to detect user input on interfaces, such as touchscreens,
keyboards, and PIN pads, by recording the heat traces left by the users' fingers after …

Low-Latency Video Anonymization for Crowd Anomaly Detection: Privacy vs. Performance

MW Asres, L Jiao, CW Omlin - arXiv preprint arXiv:2410.18717, 2024 - arxiv.org
Recent advancements in artificial intelligence promise ample potential in monitoring
applications with surveillance cameras. However, concerns about privacy and model bias …

DP Patch: ROI-based Approach of Privacy-Preserving Image Processing with Robust Classification

A Utaliyeva, SJ Hwang, YH Choi - IEEE Access, 2024 - ieeexplore.ieee.org
As machine and deep learning spread across diverse aspects of our society, the concerns
about the privacy of the data are getting stronger, particularly in scenarios where sensitive …