Ambra Demontis
Ambra Demontis
Assistant Professor at University of Cagliari
Verified email at - Homepage
Cited by
Cited by
Towards poisoning of deep learning algorithms with back-gradient optimization
L Muñoz-González, B Biggio, A Demontis, A Paudice, V Wongrassamee, ...
Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security …, 2017
Adversarial malware binaries: Evading deep learning for malware detection in executables
B Kolosnjaji, A Demontis, B Biggio, D Maiorca, G Giacinto, C Eckert, ...
2018 26th European signal processing conference (EUSIPCO), 533-537, 2018
Yes, machine learning can be more secure! a case study on android malware detection
A Demontis, M Melis, B Biggio, D Maiorca, D Arp, K Rieck, I Corona, ...
IEEE Transactions on Dependable and Secure Computing, 2017
Why do adversarial attacks transfer? explaining transferability of evasion and poisoning attacks
A Demontis, M Melis, M Pintor, M Jagielski, B Biggio, A Oprea, ...
28th {USENIX} Security Symposium ({USENIX} Security 19), 321-338, 2019
Is deep learning safe for robot vision? adversarial examples against the icub humanoid
M Melis, A Demontis, B Biggio, G Brown, G Fumera, F Roli
Proceedings of the IEEE International Conference on Computer Vision …, 2017
Secure kernel machines against evasion attacks
P Russu, A Demontis, B Biggio, G Fumera, F Roli
Proceedings of the 2016 ACM workshop on artificial intelligence and security …, 2016
On security and sparsity of linear classifiers for adversarial settings
A Demontis, P Russu, B Biggio, G Fumera, F Roli
Joint IAPR International Workshops on Statistical Techniques in Pattern …, 2016
secml: A python library for secure and explainable machine learning
M Melis, A Demontis, M Pintor, A Sotgiu, B Biggio
arXiv preprint arXiv:1912.10013, 2019
Deep neural rejection against adversarial examples
A Sotgiu, A Demontis, M Melis, B Biggio, G Fumera, X Feng, F Roli
EURASIP Journal on Information Security 2020 (1), 1-10, 2020
Adversarial detection of flash malware: Limitations and open issues
D Maiorca, A Demontis, B Biggio, F Roli, G Giacinto
Computers & Security 96, 101901, 2020
Infinity-norm support vector machines against adversarial label contamination
A Demontis, B Biggio, G Fumera, G Giacinto, F Roli
1st Italian Conference on Cybersecurity, ITASEC 2017 1816, 106-115, 2017
Do gradient-based explanations tell anything about adversarial robustness to android malware?
M Melis, M Scalas, A Demontis, D Maiorca, B Biggio, G Giacinto, F Roli
International Journal of Machine Learning and Cybernetics 13 (1), 217-232, 2022
Domain Knowledge Alleviates Adversarial Attacks in Multi-Label Classifiers
S Melacci, G Ciravegna, A Sotgiu, A Demontis, B Biggio, M Gori, F Roli
arXiv preprint arXiv:2006.03833, 2020
Super-sparse learning in similarity spaces
A Demontis, M Melis, B Biggio, G Fumera, F Roli
IEEE Computational Intelligence Magazine 11 (4), 36-45, 2016
Super-sparse regression for fast age estimation from faces at test time
A Demontis, B Biggio, G Fumera, F Roli
International Conference on Image Analysis and Processing, 551-562, 2015
The Threat of Offensive AI to Organizations
Y Mirsky, A Demontis, J Kotak, R Shankar, D Gelei, L Yang, X Zhang, ...
arXiv preprint arXiv:2106.15764, 2021
Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples
M Pintor, L Demetrio, A Sotgiu, G Manca, A Demontis, N Carlini, B Biggio, ...
arXiv preprint arXiv:2106.09947, 2021
Securing Machine Learning against Adversarial Attacks
A Demontis, F Roli, B Biggio
Why Adversarial Reprogramming Works, When It Fails, and How to Tell the Difference
Y Zheng, X Feng, Z Xia, X Jiang, A Demontis, M Pintor, B Biggio, F Roli
arXiv preprint arXiv:2108.11673, 2021
Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions
AE Cinà, K Grosse, S Vascon, A Demontis, B Biggio, F Roli, M Pelillo
arXiv preprint arXiv:2106.07214, 2021
The system can't perform the operation now. Try again later.
Articles 1–20