Trustworthy AI: From principles to practices

B Li, P Qi, B Liu, S Di, J Liu, J Pei, J Yi… - ACM Computing Surveys, 2023 - dl.acm.org
The rapid development of Artificial Intelligence (AI) technology has enabled the deployment
of various systems based on it. However, many current AI systems are found vulnerable to …

Explainability of deep vision-based autonomous driving systems: Review and challenges

É Zablocki, H Ben-Younes, P Pérez, M Cord - International Journal of …, 2022 - Springer
This survey reviews explainability methods for vision-based self-driving systems trained with
behavior cloning. The concept of explainability has several facets and the need for …

Laion-5b: An open large-scale dataset for training next generation image-text models

C Schuhmann, R Beaumont, R Vencu… - Advances in …, 2022 - proceedings.neurips.cc
Groundbreaking language-vision architectures like CLIP and DALL-E proved the utility of
training on large amounts of noisy image-text data, without relying on expensive accurate …

Countering malicious deepfakes: Survey, battleground, and horizon

F Juefei-Xu, R Wang, Y Huang, Q Guo, L Ma… - International journal of …, 2022 - Springer
The creation or manipulation of facial appearance through deep generative approaches,
known as DeepFake, have achieved significant progress and promoted a wide range of …

Coming down to earth: Satellite-to-street view synthesis for geo-localization

A Toker, Q Zhou, M Maximov… - Proceedings of the …, 2021 - openaccess.thecvf.com
The goal of cross-view image based geo-localization is to determine the location of a given
street view image by matching it against a collection of geo-tagged satellite images. This …

UAV-satellite view synthesis for cross-view geo-localization

X Tian, J Shao, D Ouyang… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
The goal of cross-view image matching based on geo-localization is to determine the
location of a given ground-view image (front view) by matching it with a group of satellite …

Openforensics: Large-scale challenging dataset for multi-face forgery detection and segmentation in-the-wild

TN Le, HH Nguyen, J Yamagishi… - Proceedings of the …, 2021 - openaccess.thecvf.com
The proliferation of deepfake media is raising concerns among the public and relevant
authorities. It has become essential to develop countermeasures against forged faces in …

Attribute-preserving face dataset anonymization via latent code optimization

S Barattin, C Tzelepis, I Patras… - Proceedings of the …, 2023 - openaccess.thecvf.com
This work addresses the problem of anonymizing the identity of faces in a dataset of images,
such that the privacy of those depicted is not violated, while at the same time the dataset is …

Personalized and invertible face de-identification by disentangled identity information manipulation

J Cao, B Liu, Y Wen, R **e… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
The popularization of intelligent devices including smartphones and surveillance cameras
results in more serious privacy issues. De-identification is regarded as an effective tool for …

F-TPE: Flexible thumbnail-preserving encryption based on multi-pixel sum-preserving encryption

Y Zhang, W Zhou, R Zhao, X Zhang… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
People are accustomed to utilizing mobile phones to capture images and uploading them to
the cloud due to various incomparable advantages such as saving the storage space on the …