E-LIB Suche - Ergebnisse für: Sotgiu, Angelo

1

Detecting Attacks Against Deep Reinforcement Learning for A..:

, In: 2023 International Conference on Machine Learning and Cybernetics (ICMLC),

Pintor, Maura ; Demetrio, Luca ; Sotgiu, Angelo... - p. 57-62 , 2023

Link: https://doi.org/10.1109/..

2

ImageNet-Patch: A dataset for benchmarking machine learning..:

Pintor, Maura ; Angioni, Daniele ; Sotgiu, Angelo...
Pattern Recognition. 134 (2023) - p. 109064 , 2023

Link: https://doi.org/10.1016/..

3

Domain Knowledge Alleviates Adversarial Attacks in Multi-La..:

Melacci, Stefano ; Ciravegna, Gabriele ; Sotgiu, Angelo...
IEEE Transactions on Pattern Analysis and Machine Intelligence. 44 (2022) 12 - p. 9944-9959 , 2022

Link: https://doi.org/10.1109/..

4

secml: Secure and explainable machine learning in Python:

Pintor, Maura ; Demetrio, Luca ; Sotgiu, Angelo...
SoftwareX. 18 (2022) - p. 101095 , 2022

Link: https://doi.org/10.1016/..

5

FADER: Fast adversarial example rejection:

Crecchi, Francesco ; Melis, Marco ; Sotgiu, Angelo..
Neurocomputing. 470 (2022) - p. 257-268 , 2022

Link: https://doi.org/10.1016/..

6

Explainability-based Debugging of Machine Learning for Vuln..:

, In: Proceedings of the 17th International Conference on Availability, Reliability and Security,

Sotgiu, Angelo ; Pintor, Maura ; Biggio, Battista - p. 1-8 , 2022

Link: https://dl.acm.org/doi/1..

7

Deep neural rejection against adversarial examples:

Sotgiu, Angelo ; Demontis, Ambra ; Melis, Marco...
EURASIP Journal on Information Security. 2020 (2020) 1 - p. , 2020

Link: https://doi.org/10.1186/..

8

Evaluating Adversarial Robustness of Detection-based Defens..:

SOTGIU, ANGELO
https://hdl.handle.net/11584/357305. , 2023

Link: https://hdl.handle.net/1..

9

ImageNet-Patch: A Dataset for Benchmarking Machine Learning..:

Pintor, Maura ; Angioni, Daniele ; Sotgiu, Angelo...
http://arxiv.org/abs/2203.04412. , 2022

Link: http://arxiv.org/abs/220..

10

Indicators of Attack Failure: Debugging and Improving Optim..:

Pintor, Maura ; Demetrio, Luca ; Sotgiu, Angelo...
http://arxiv.org/abs/2106.09947. , 2021

Link: http://arxiv.org/abs/210..

11

Domain Knowledge Alleviates Adversarial Attacks in Multi-La..:

Melacci, Stefano ; Ciravegna, Gabriele ; Sotgiu, Angelo...
http://arxiv.org/abs/2006.03833. , 2020

Link: http://arxiv.org/abs/200..

12

FADER: Fast Adversarial Example Rejection:

Crecchi, Francesco ; Melis, Marco ; Sotgiu, Angelo..
http://arxiv.org/abs/2010.09119. , 2020

Link: http://arxiv.org/abs/201..

13

Deep Neural Rejection against Adversarial Examples:

Sotgiu, Angelo ; Demontis, Ambra ; Melis, Marco...
http://arxiv.org/abs/1910.00470. , 2019

Link: http://arxiv.org/abs/191..

14

secml: A Python Library for Secure and Explainable Machine ..:

Pintor, Maura ; Demetrio, Luca ; Sotgiu, Angelo...
http://arxiv.org/abs/1912.10013. , 2019

Link: http://arxiv.org/abs/191..

15

IntelliAV: Building an Effective On-Device Android Malware ..:

Ahmadi, Mansour ; Sotgiu, Angelo ; Giacinto, Giorgio
http://arxiv.org/abs/1802.01185. , 2018

Link: http://arxiv.org/abs/180..