| Wild patterns reloaded: A survey of machine learning security against training data poisoning AE Cinà, K Grosse, A Demontis, S Vascon, W Zellinger, BA Moser, ... ACM Computing Surveys 55 (13s), 1-39, 2023 | 96 | 2023 |
| A black-box adversarial attack for poisoning clustering AE Cinà, A Torcinovich, M Pelillo Pattern Recognition 122, 108306, 2022 | 48 | 2022 |
| Machine learning security against data poisoning: Are we there yet? AE Cinà, K Grosse, A Demontis, B Biggio, F Roli, M Pelillo IEEE Computer 57 (Issue 3), 26 - 34, 2024 | 34 | 2024 |
| Energy-latency attacks via sponge poisoning AE Cinà, A Demontis, B Biggio, F Roli, M Pelillo arXiv preprint arXiv:2203.08147, 2022 | 20 | 2022 |
| The hammer and the nut: Is bilevel optimization really needed to poison linear classifiers? AE Cinà, S Vascon, A Demontis, B Biggio, F Roli, M Pelillo 2021 International Joint Conference on Neural Networks (IJCNN), 1-8, 2021 | 15 | 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 | 15 | 2021 |
| Minimizing energy consumption of deep learning models by energy-aware training D Lazzaro, AE Cinà, M Pintor, A Demontis, B Biggio, F Roli, M Pelillo International Conference on Image Analysis and Processing, 515-526, 2023 | 6 | 2023 |
| Conning the Crypto Conman: End-to-End Analysis of Cryptocurrency-based Technical Support Scams B Acharya, M Saad, AE Cinà, L Schönherr, HD Nguyen, A Oest, ... 2024 IEEE Symposium on Security and Privacy (SP), 156-156, 2024 | 4 | 2024 |
| AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples AE Cinà, J Rony, M Pintor, L Demetrio, A Demontis, B Biggio, IB Ayed, ... arXiv preprint arXiv:2404.19460, 2024 | 2 | 2024 |
| σ-zero: Gradient-based Optimization of 𝓁0-norm Adversarial Examples. AE Cinà, F Villani, M Pintor, L Schönherr, B Biggio, M Pelillo CoRR, 2024 | 2 | 2024 |
| On the Limitations of Model Stealing with Uncertainty Quantification Models D Pape, S Däubener, T Eisenhofer, AE Cinà, L Schönherr European Symposium on Artificial Neural Networks, Computational Intelligence …, 2023 | 2 | 2023 |
| Security of Machine Learning (Dagstuhl Seminar 22281) B Biggio, N Carlini, P Laskov, K Rieck, AE Cinà Dagstuhl Reports 12 (7), 41--61, 2023 | 2 | 2023 |
| Hardening RGB-D object recognition systems against adversarial patch attacks Y Zheng, L Demetrio, AE Cinà, X Feng, Z Xia, X Jiang, A Demontis, ... Information Sciences 651, 119701, 2023 | 1 | 2023 |
| Sonic: Fast and Transferable Data Poisoning on Clustering Algorithms F Villani, D Lazzaro, AE Cinà, M Dell'Amico, B Biggio, F Roli arXiv preprint arXiv:2408.07558, 2024 | | 2024 |
| Understanding XAI Through the Philosopher's Lens: A Historical Perspective M Mattioli, AE Cinà, M Pelillo arXiv preprint arXiv:2407.18782, 2024 | | 2024 |
| Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis Z Chen, L Demetrio, S Gupta, X Feng, Z Xia, AE Cinà, M Pintor, L Oneto, ... arXiv preprint arXiv:2406.10090, 2024 | | 2024 |
| -zero: Gradient-based Optimization of -norm Adversarial Examples AE Cinà, F Villani, M Pintor, L Schönherr, B Biggio, M Pelillo arXiv preprint arXiv:2402.01879, 2024 | | 2024 |
| The Imitation Game: Exploring Brand Impersonation Attacks on Social Media Platforms B Acharya, D Lazzaro, E López-Morales, A Oest, M Saad, AE Cinà, ... 33rd USENIX Security Symposium, 2024 | | 2024 |
| Vector Flows and the Capacity of a Discrete Memoryless Channel G Beretta, G Chiarot, AE Cinà, M Pelillo arXiv preprint arXiv:2312.16472, 2023 | | 2023 |
| Vulnerability of Machine Learning: A Study on Poisoning Attacks AE Cina Università Ca'Foscari Venezia, 2023 | | 2023 |
Battista BiggioFull Professor, University of Cagliari, ItalyVerified email at unica.it