Παρακαλώ χρησιμοποιήστε αυτό το αναγνωριστικό για να παραπέμψετε ή να δημιουργήσετε σύνδεσμο προς αυτό το τεκμήριο:
https://hdl.handle.net/20.500.14279/27106
Τίτλος: | Local Competition and Stochasticity for Adversarial Robustness in Deep Learning |
Συγγραφείς: | Panousis, Konstantinos P. Chatzis, Sotirios P. Alexos, Antonios Theodoridis, Sergios |
Major Field of Science: | Engineering and Technology |
Field Category: | Other Engineering and Technologies |
Λέξεις-κλειδιά: | Computer Science - Learning;Machine Learning |
Ημερομηνία Έκδοσης: | 4-Ιαν-2021 |
Πηγή: | International Conference on Artificial Intelligence and Statistics. PMLR, 2021. p. 3862-3870 |
Project: | aRTIFICIAL iNTELLIGENCE for the Deaf (aiD) |
Conference: | International Conference on Artificial Intelligence and Statistics |
Περίληψη: | This work addresses adversarial robustness in deep learning by considering deep networks with stochastic local winner-takes-all (LWTA) activations. This type of network units result in sparse representations from each model layer, as the units are organized in blocks where only one unit generates a non-zero output. The main operating principle of the introduced units lies on stochastic arguments, as the network performs posterior sampling over competing units to select the winner. We combine these LWTA arguments with tools from the field of Bayesian non-parametrics, specifically the stick-breaking construction of the Indian Buffet Process, to allow for inferring the sub-part of each layer that is essential for modeling the data at hand. Then, inference is performed by means of stochastic variational Bayes. We perform a thorough experimental evaluation of our model using benchmark datasets. As we show, our method achieves high robustness to adversarial perturbations, with state-of-the-art performance in powerful adversarial attack schemes. |
URI: | https://hdl.handle.net/20.500.14279/27106 |
Rights: | Attribution-NonCommercial-NoDerivatives 4.0 International |
Type: | Conference Papers |
Affiliation: | Cyprus University of Technology University of California National and Kapodistrian University of Athens |
Publication Type: | Peer Reviewed |
Εμφανίζεται στις συλλογές: | Δημοσιεύσεις σε συνέδρια /Conference papers or poster or presentation |
Αρχεία σε αυτό το τεκμήριο:
Αρχείο | Περιγραφή | Μέγεθος | Μορφότυπος | |
---|---|---|---|---|
Local_competition.pdf | 612.4 kB | Adobe PDF | Δείτε/ Ανοίξτε |
CORE Recommender
Αυτό το τεκμήριο προστατεύεται από άδεια Άδεια Creative Commons