Publications
, “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), pp. 751-759.
(3.16 MB)
(3.16 MB), “Explaining Black-box Android Malware Detection”, in 26th European Signal Processing Conference (EUSIPCO '18), Rome, Italy, 2018, pp. 524-528. (431.78 KB)
(431.78 KB), “Fast Image Classification with Reduced Multiclass Support Vector Machines”, in 18th Int'l Conf. on Image Analysis and Processing, Genova, Italy, 2015, vol. Image Analysis and Processing (ICIAP 2015), pp. 78-88. (829.37 KB)
(829.37 KB), “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), p. 321--338. (1.09 MB)
(1.09 MB), “Deep Neural Rejection against Adversarial Examples”, EURASIP Journal on Information Security, vol. 5, 2020.
, “Do Gradient-Based Explanations Tell Anything About Adversarial Robustness to Android Malware?”, International Journal of Machine Learning and Cybernetics, vol. 13, pp. 217-232, 2022. (1.2 MB)
(1.2 MB), “FADER: Fast adversarial example rejection”, Neurocomputing, vol. 470, pp. 257-268, 2022.
, “secml: A Python Library for Secure and Explainable Machine Learning”, SoftwareX, 2022.
, “Super-sparse Learning in Similarity Spaces”, IEEE Computational Intelligence Magazine, vol. 11, no. 4, pp. 36-45, 2016. (555.22 KB)
(555.22 KB), “Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detection”, IEEE Trans. Dependable and Secure Computing, vol. 16, no. 4, pp. 711-724, 2019. (3.61 MB)
(3.61 MB)
