Zobrazeno 1 - 10
of 125
pro vyhledávání: '"Mario Fritz"'
Autor:
Rakibul Hasan, Mario Fritz
Publikováno v:
Proceedings on Privacy Enhancing Technologies. 2022:245-262
Education technologies (EdTech) are becoming pervasive due to their cost-effectiveness, accessibility, and scalability. They also experienced accelerated market growth during the recent pandemic. EdTech collects massive amounts of students’ behavio
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::116aef262e69867847b55e883b1977dc
https://doi.org/10.2478/popets-2022-0044
https://doi.org/10.2478/popets-2022-0044
Publikováno v:
GCPR
International Journal of Computer Vision
Pattern Recognition
International Journal of Computer Vision
Pattern Recognition
Today’s deep learning systems deliver high performance based on end-to-end training but are notoriously hard to inspect. We argue that there are at least two reasons making inspectability challenging: (i) representations are distributed across hund
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::01d9c92e9fd3747a5063fb6966544c79
https://doi.org/10.1007/s11263-021-01498-0
https://doi.org/10.1007/s11263-021-01498-0
Publikováno v:
Neurocomputing
Predicting the target of visual search from human eye fixations (gaze) is a difficult problem with many applications, e.g. in human-computer interaction. While previous work has focused on predicting specific search target instances, we propose the f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::622a8ec87a3690749cd3bbda297556d5
Publikováno v:
AISec@CCS
Machine learning models are commonly trained on sensitive and personal data such as pictures, medical records, financial records, etc. A serious breach of the privacy of this training set occurs when an adversary is able to decide whether or not a sp
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::a11aff8355a9571403147d6224ab5feb
https://doi.org/10.1145/3474369.3486876
https://doi.org/10.1145/3474369.3486876
Autor:
Mario Fritz, Sahar Abdelnabi
Publikováno v:
MTD@CCS
Machine learning models are now widely deployed in real-world applications. However, the existence of adversarial examples has been long considered a real threat to such models. While numerous defenses aiming to improve the robustness have been propo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::112b92cbafc2b60acc48e7d07a9e2ed6
http://arxiv.org/abs/2102.05104
http://arxiv.org/abs/2102.05104
Publikováno v:
CVPR
IEEE/CVF Conference on Computer Vision and Pattern Recognition
IEEE/CVF Conference on Computer Vision and Pattern Recognition
Accurate prediction of pedestrian and bicyclist paths is integral to the development of reliable autonomous vehicles in dense urban environments. The interactions between vehicle and pedestrian or bicyclist have a significant impact on the trajectori
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::4aeb130287d4418ca01c367e352af032
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030712778
GCPR
GCPR
Deep learning enables impressive performance in image recognition using large-scale artificially-balanced datasets. However, real-world datasets exhibit highly class-imbalanced distributions, yielding two main challenges: relative imbalance amongst t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::fd871f2fe2af56fe90f36cc7e62b01fb
https://doi.org/10.1007/978-3-030-71278-5_7
https://doi.org/10.1007/978-3-030-71278-5_7
Publikováno v:
IJCAI
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
The rapid advances in deep generative models over the past years have led to highly {realistic media, known as deepfakes,} that are commonly indistinguishable from real to human eyes. These advances make assessing the authenticity of visual data incr
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::69931eb503360d423b4f0ebe1e2a0aee
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783030712778
GCPR
GCPR
Prediction of trajectories such as that of pedestrians is crucial to the performance of autonomous agents. While previous works have leveraged conditional generative models like GANs and VAEs for learning the likely future trajectories, accurately mo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::52c4177f9c730a218aefae94aa205add
https://doi.org/10.1007/978-3-030-71278-5_20
https://doi.org/10.1007/978-3-030-71278-5_20
Publikováno v:
Communications in Computer and Information Science ISBN: 9783030937324
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::3df3e2aefe25b693c8a5fd765b3dbb3a
https://doi.org/10.1007/978-3-030-93733-1_8
https://doi.org/10.1007/978-3-030-93733-1_8