Publications

Export 15 results:
Filters: Author is Ambra Demontis  [Clear All Filters]
Journal Article
A. Demontis, Melis, M., Biggio, B., Maiorca, D., Arp, D., Rieck, K., Corona, I., Giacinto, G., e Roli, F., «Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detection», IEEE Trans. Dependable and Secure Computing, vol 16, n° 4, pagg 711-724, 2019. (3.61 MB)
A. Demontis, Melis, M., Biggio, B., Fumera, G., e Roli, F., «Super-sparse Learning in Similarity Spaces», IEEE Computational Intelligence Magazine, vol 11, n° 4, pagg 36-45, 2016. (555.22 KB)
M. Pintor, Demetrio, L., Sotgiu, A., Melis, M., Demontis, A., e Biggio, B., «secml: A Python Library for Secure and Explainable Machine Learning», SoftwareX, 2022.
M. Melis, Scalas, M., Demontis, A., Maiorca, D., Biggio, B., Giacinto, G., e Roli, F., «Do Gradient-Based Explanations Tell Anything About Adversarial Robustness to Android Malware?», International Journal of Machine Learning and Cybernetics, vol 13, pagg 217-232, 2022. (1.2 MB)
A. Sotgiu, Demontis, A., Melis, M., Biggio, B., Fumera, G., Feng, X., e Roli, F., «Deep Neural Rejection against Adversarial Examples», EURASIP Journal on Information Security, vol 5, 2020.
D. Maiorca, Demontis, A., Biggio, B., Roli, F., e Giacinto, G., «Adversarial Detection of Flash Malware: Limitations and Open Issues», Computers & Security, vol 96, 2020. (1.08 MB)
Conference Proceedings
A. Demontis, Biggio, B., Fumera, G., Giacinto, G., e Roli, F., «Infinity-norm Support Vector Machines against Adversarial Label Contamination», 1st Italian Conference on CyberSecurity (ITASEC). Venice, Italy , pagg 106-115, 2017. (504.93 KB)
Conference Paper
A. Demontis, Melis, M., Pintor, M., Jagielski, M., Biggio, B., Oprea, A., Nita-Rotaru, C., e Roli, F., «Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks», in 28th Usenix Security Symposium, Santa Clara, California, USA, 2019, vol 28th {USENIX} Security Symposium ({USENIX} Security 19), pag 321--338. (1.09 MB)
L. Muñoz-González, Biggio, B., Demontis, A., Paudice, A., Wongrassamee, V., Lupu, E. C., e Roli, F., «Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization», in 10th ACM Workshop on Artificial Intelligence and Security, 2017, pagg 27-38. (4.08 MB)
A. Demontis, Biggio, B., Fumera, G., e Roli, F., «Super-Sparse Regression for Fast Age Estimation From Faces at Test Time», in 18th Int'l Conf. on Image Analysis and Processing (ICIAP), Genova, Italy, 2015, vol Image Analysis and Processing (ICIAP 2015), pagg 551-562. (678.7 KB)
A. Demontis, Russu, P., Biggio, B., Fumera, G., e Roli, F., «On Security and Sparsity of Linear Classifiers for Adversarial Settings», in Joint IAPR Int'l Workshop on Structural, Syntactic, and Statistical Pattern Recognition, Merida, Mexico, 2016, vol 10029 of LNCS, pagg 322-332. (425.68 KB)
P. Russu, Demontis, A., Biggio, B., Fumera, G., e Roli, F., «Secure Kernel Machines against Evasion Attacks», in 9th ACM Workshop on Artificial Intelligence and Security, Vienna, Austria, 2016, pagg 59-69. (686.41 KB)
A. Emanuele Cinà, Vascon, S., Demontis, A., Biggio, B., Roli, F., e Pelillo, M., «The Hammer and the Nut: Is Bilevel Optimization Really Needed to Poison Linear Classifiers?», in International Joint Conference on Neural Networks, (IJCNN) 2021, Shenzhen, China, 2021, pagg 1–8.
M. Melis, Demontis, A., Biggio, B., Brown, G., Fumera, G., e Roli, F., «Is Deep Learning Safe for Robot Vision? Adversarial Examples against the iCub Humanoid», in ICCV 2017 Workshop on Vision in Practice on Autonomous Robots (ViPAR), Venice, Italy, 2017, vol 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), pagg 751-759. (3.16 MB)
B. Kolosnjaji, Demontis, A., Biggio, B., Maiorca, D., Giacinto, G., Eckert, C., e Roli, F., «Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executables», in 2018 26th European Signal Processing Conference (EUSIPCO), Rome, 2018, pagg 533-537. (674.62 KB)