Publications
, «Diversified Sensitivity based Undersampling for Imbalance Classification Problems», IEEE Transactions on Cybernetics, In Press.
(1.91 MB)
(1.91 MB), «On Reducing the Effect of Covariate Factors in Gait Recognition: a Classifier Ensemble Method», IEEE Transactions on Pattern Analysis and Machine Intelligence, In Press. (311.43 KB) (151.4 KB)
(311.43 KB) (151.4 KB), «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)
(1.2 MB), «Adversarial EXEmples: A Survey and Experimental Evaluation of Practical Attacks on Machine Learning for Windows Malware Detection», ACM Trans. Priv. Secur., vol 24, 2021.
, «Empirical Assessment of Generating Adversarial Configurations for Software Product Lines», Empirical Software Engineering, vol 26, n° 6, 2021. (1.29 MB)
(1.29 MB), «Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints», in NeurIPS, 2021.
, «Functionality-Preserving Black-Box Optimization of Adversarial Windows Malware», IEEE Transactions on Information Forensics and Security, vol 16, pagg 3469-3478, 2021.
, «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.
, «Adversarial Detection of Flash Malware: Limitations and Open Issues», Computers & Security, vol 96, 2020. (1.08 MB)
(1.08 MB), «Deep Neural Rejection against Adversarial Examples», EURASIP Journal on Information Security, vol 5, 2020.
, «DEICTIC: a Compositional and Declarative Gesture Description based on Hidden Markov Model», International Journal of Human-Computer Studies, vol 122, pag 20, 2019. (1.69 MB)
(1.69 MB), «Explaining Vulnerabilities of Deep Learning to Adversarial Malware Binaries», in 3rd Italian Conference on Cyber Security, ITASEC 2019, Pisa, Italy, 2019, vol 2315. (801.85 KB)
(801.85 KB), «Towards Quality Assurance of Software Product Lines with Adversarial Configurations», in Proceedings of the 23rd International Systems and Software Product Line Conference - Volume A, New York, NY, USA, 2019, pagg 277–288. (2.09 MB)
(2.09 MB), «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)
(1.09 MB), «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)
(3.61 MB), «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)
(674.62 KB), «Explaining Black-box Android Malware Detection», in 26th European Signal Processing Conference (EUSIPCO '18), Rome, Italy, 2018, pagg 524-528. (431.78 KB)
(431.78 KB), «Multi-Stage Ranking Approach for Fast Person Re-Identification», IET Computer Vision, vol 12, n° 4, pag 7, 2018. (1.07 MB)
(1.07 MB), «Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning», Pattern Recognition, vol 84, pagg 317-331, 2018. (3.76 MB)
(3.76 MB), «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)
(3.16 MB), «Deepsquatting: Learning-based Typosquatting Detection at Deeper Domain Levels», in 16th International Conference of the Italian Association for Artificial Intelligence (AI*IA 2017), 2017, vol 10640 of LNCS, pagg 347-358. (1.21 MB)
(1.21 MB), «DeltaPhish: Detecting Phishing Webpages in Compromised Websites», 22nd European Symposium on Research in Computer Security (ESORICS), vol 10492. Springer International Publishing, Norway, September 11-15, 2017, pagg 370–388, 2017. (4.13 MB)
(4.13 MB), «Designing multi-label classifiers that maximize F measures: state of the art», Pattern Recognition, vol 61, 2017. (452.28 KB)
(452.28 KB), «A Parameter Randomization Approach for Constructing Classifier Ensembles», Pattern Recognition, vol 69, pagg 1-13, 2017. (448.73 KB)
(448.73 KB), «Randomized Prediction Games for Adversarial Machine Learning», IEEE Transactions on Neural Networks and Learning Systems, vol 28, n° 11, pagg 2466-2478, 2017. (1.52 MB) (256.21 KB)
(1.52 MB) (256.21 KB)
