Standard
Self-Supervised Representation Learning for Adversarial Attack Detection. /
Li, Yi; Angelov, Plamen; Suri, Neeraj.
Computer Vision – ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part I. ed. / Aleš Leonardis; Elisa Ricci; Stefan Roth; Olga Russakovsky; Torsten Sattler; Gül Varol. Cham: Springer, 2024. p. 236-252 (Lecture Notes in Computer Science; Vol. 15118).
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Harvard
Li, Y, Angelov, P & Suri, N 2024,
Self-Supervised Representation Learning for Adversarial Attack Detection. in A Leonardis, E Ricci, S Roth, O Russakovsky, T Sattler & G Varol (eds),
Computer Vision – ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part I. Lecture Notes in Computer Science, vol. 15118, Springer, Cham, pp. 236-252.
https://doi.org/10.1007/978-3-031-73027-6_14
APA
Li, Y., Angelov, P., & Suri, N. (2024).
Self-Supervised Representation Learning for Adversarial Attack Detection. In A. Leonardis, E. Ricci, S. Roth, O. Russakovsky, T. Sattler, & G. Varol (Eds.),
Computer Vision – ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part I (pp. 236-252). (Lecture Notes in Computer Science; Vol. 15118). Springer.
https://doi.org/10.1007/978-3-031-73027-6_14
Vancouver
Li Y, Angelov P, Suri N.
Self-Supervised Representation Learning for Adversarial Attack Detection. In Leonardis A, Ricci E, Roth S, Russakovsky O, Sattler T, Varol G, editors, Computer Vision – ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part I. Cham: Springer. 2024. p. 236-252. (Lecture Notes in Computer Science). Epub 2024 Oct 2. doi: 10.1007/978-3-031-73027-6_14
Author
Li, Yi ; Angelov, Plamen ; Suri, Neeraj. /
Self-Supervised Representation Learning for Adversarial Attack Detection. Computer Vision – ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part I. editor / Aleš Leonardis ; Elisa Ricci ; Stefan Roth ; Olga Russakovsky ; Torsten Sattler ; Gül Varol. Cham : Springer, 2024. pp. 236-252 (Lecture Notes in Computer Science).
Bibtex
@inproceedings{e54f0b3c0bce46e9abd17146788e44c0,
title = "Self-Supervised Representation Learning for Adversarial Attack Detection",
abstract = "Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised representation learning framework for the adversarial attack detection task to address this drawback. Firstly, we map the pixels of augmented input images into an embedding space. Then, we employ the prototype-wise contrastive estimation loss to cluster prototypes as latent variables. Additionally, drawing inspiration from the concept of memory banks, we introduce a discrimination bank to distinguish and learn representations for each individual instance that shares the same or a similar prototype, establishing a connection between instances and their associated prototypes. Experimental results show that, compared to various benchmark self-supervised vision learning models and supervised adversarial attack detection methods, the proposed model achieves state-of-the-art performance on the adversarial attack detection task across a wide range of images.",
author = "Yi Li and Plamen Angelov and Neeraj Suri",
year = "2024",
month = nov,
day = "26",
doi = "10.1007/978-3-031-73027-6_14",
language = "English",
isbn = "9783031730269",
series = "Lecture Notes in Computer Science",
publisher = "Springer",
pages = "236--252",
editor = "Ale{\v s} Leonardis and Elisa Ricci and Stefan Roth and Olga Russakovsky and Torsten Sattler and Varol, {G{\"u}l }",
booktitle = "Computer Vision – ECCV 2024",
}
RIS
TY - GEN
T1 - Self-Supervised Representation Learning for Adversarial Attack Detection
AU - Li, Yi
AU - Angelov, Plamen
AU - Suri, Neeraj
PY - 2024/11/26
Y1 - 2024/11/26
N2 - Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised representation learning framework for the adversarial attack detection task to address this drawback. Firstly, we map the pixels of augmented input images into an embedding space. Then, we employ the prototype-wise contrastive estimation loss to cluster prototypes as latent variables. Additionally, drawing inspiration from the concept of memory banks, we introduce a discrimination bank to distinguish and learn representations for each individual instance that shares the same or a similar prototype, establishing a connection between instances and their associated prototypes. Experimental results show that, compared to various benchmark self-supervised vision learning models and supervised adversarial attack detection methods, the proposed model achieves state-of-the-art performance on the adversarial attack detection task across a wide range of images.
AB - Supervised learning-based adversarial attack detection methods rely on a large number of labeled data and suffer significant performance degradation when applying the trained model to new domains. In this paper, we propose a self-supervised representation learning framework for the adversarial attack detection task to address this drawback. Firstly, we map the pixels of augmented input images into an embedding space. Then, we employ the prototype-wise contrastive estimation loss to cluster prototypes as latent variables. Additionally, drawing inspiration from the concept of memory banks, we introduce a discrimination bank to distinguish and learn representations for each individual instance that shares the same or a similar prototype, establishing a connection between instances and their associated prototypes. Experimental results show that, compared to various benchmark self-supervised vision learning models and supervised adversarial attack detection methods, the proposed model achieves state-of-the-art performance on the adversarial attack detection task across a wide range of images.
U2 - 10.1007/978-3-031-73027-6_14
DO - 10.1007/978-3-031-73027-6_14
M3 - Conference contribution/Paper
SN - 9783031730269
T3 - Lecture Notes in Computer Science
SP - 236
EP - 252
BT - Computer Vision – ECCV 2024
A2 - Leonardis, Aleš
A2 - Ricci, Elisa
A2 - Roth, Stefan
A2 - Russakovsky, Olga
A2 - Sattler, Torsten
A2 - Varol, Gül
PB - Springer
CY - Cham
ER -
