Sfoglia per Autore DEMONTIS, AMBRA
Machine Learning Security Against Data Poisoning: Are We There Yet?
2024-01-01 Cinà, Antonio Emanuele; Grosse, Kathrin; Demontis, Ambra; Biggio, Battista; Roli, Fabio; Pelillo, Marcello
Improving Fast Minimum-Norm Attacks with Hyperparameter Optimization
2023-01-01 Floris, Giuseppe; Mura, Raffaele; Scionis, Luca; Piras, Giorgio; Pintor, Maura; Demontis, Ambra; Biggio, Battista
Hardening RGB-D object recognition systems against adversarial patch attacks
2023-01-01 Zheng, Yang; Demetrio, Luca; Cinà, Antonio Emanuele; Feng, Xiaoyi; Xia, Zhaoqiang; Jiang, Xiaoyue; Demontis, Ambra; Biggio, Battista; Roli, Fabio
Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning
2023-01-01 Emanuele Cinà, Antonio; Grosse, Kathrin; Demontis, Ambra; Vascon, Sebastiano; Zellinger, Werner; Moser, Bernhard A.; Oprea, Alina; Biggio, Battista; Pelillo, Marcello; Roli, Fabio
Minimizing Energy Consumption of Deep Learning Models by Energy-Aware Training
2023-01-01 Lazzaro, Dario; Cinà, Antonio Emanuele; Pintor, Maura; Demontis, Ambra; Biggio, Battista; Roli, Fabio; Pelillo, Marcello
Stateful detection of adversarial reprogramming
2023-01-01 Zheng, Yang; Feng, Xiaoyi; Xia, Zhaoqiang; Jiang, Xiaoyue; Pintor, Maura; Demontis, Ambra; Biggio, Battista; Roli, Fabio
Cybersecurity and AI: The PRALab Research Experience
2023-01-01 Pintor, Maura; Orru, Giulia; Maiorca, Davide; Demontis, Ambra; Demetrio, Luca; Marcialis, GIAN LUCA; Biggio, Battista; Roli, Fabio
AI Security and Safety: The PRALab Research Experience
2023-01-01 Demontis, Ambra; Pintor, Maura; Demetrio, Luca; Sotgiu, Angelo; Angioni, Daniele; Piras, Giorgio; Gupta, Srishti; Biggio, Battista; Roli, Fabio
ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches
2023-01-01 Pintor, Maura; Angioni, Daniele; Sotgiu, Angelo; Demetrio, Luca; Demontis, Ambra; Biggio, Battista; Roli, Fabio
Detecting Attacks Against Deep Reinforcement Learning for Autonomous Driving
2023-01-01 Pintor, Maura; Demetrio, Luca; Sotgiu, Angelo; Lin, HSIAO-YING; Fang, Chengfang; Demontis, Ambra; Biggio, Battista
Samples on Thin Ice: Re-evaluating Adversarial Pruning of Neural Networks
2023-01-01 Piras, Giorgio; Pintor, Maura; Demontis, Ambra; Biggio, Battista
Why adversarial reprogramming works, when it fails, and how to tell the difference
2023-01-01 Zheng, Yang; Feng, Xiaoyi; Xia, Zhaoqiang; Jiang, Xiaoyue; Demontis, Ambra; Pintor, Maura; Biggio, Battista; Roli, Fabio
The Threat of Offensive AI to Organizations
2023-01-01 Mirsky, Y.; Demontis, A.; Kotak, J.; Shankar, R.; Gelei, D.; Yang, L.; Zhang, X.; Pintor, M.; Lee, W.; Elovici, Y.; Biggio, B.
Domain Knowledge Alleviates Adversarial Attacks in Multi-Label Classifiers
2022-01-01 Melacci, S.; Ciravegna, G.; Sotgiu, A.; Demontis, A.; Biggio, B.; Gori, M.; Roli, F.
Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples
2022-01-01 Pintor, Maura; Demetrio, Luca; Sotgiu, Angelo; Demontis, Ambra; Carlini, Nicholas; Biggio, Battista; Roli, Fabio
A Hybrid Training-Time and Run-Time Defense Against Adversarial Attacks in Modulation Classification
2022-01-01 Zhang, L; Lambotharan, S; Zheng, G; Liao, Gs; Demontis, A; Roli, F
Do gradient-based explanations tell anything about adversarial robustness to android malware?
2022-01-01 Melis, M.; Scalas, M.; Demontis, A.; Maiorca, D.; Biggio, B.; Giacinto, G.; Roli, F.
secml: Secure and explainable machine learning in Python
2022-01-01 Pintor, Maura; Demetrio, Luca; Sotgiu, Angelo; Melis, Marco; Demontis, Ambra; Biggio, Battista
The hammer and the nut: is bilevel optimization really needed to poison linear classifiers?
2021-01-01 Cina, A. E.; Vascon, S.; Demontis, A.; Biggio, B.; Roli, F.; Pelillo, M.
Deep neural rejection against adversarial examples
2020-01-01 Sotgiu, Angelo; Demontis, Ambra; Melis, Marco; Biggio, Battista; Fumera, Giorgio; Feng, Xiaoyi; Roli, Fabio
Titolo | Data di pubblicazione | Autore(i) | Rivista | Editore |
---|---|---|---|---|
Machine Learning Security Against Data Poisoning: Are We There Yet? | 1-gen-2024 | Cinà, Antonio Emanuele; Grosse, Kathrin; Demontis, Ambra; Biggio, Battista; Roli, Fabio; Pelillo, Marcello | COMPUTER | - |
Improving Fast Minimum-Norm Attacks with Hyperparameter Optimization | 1-gen-2023 | Floris, Giuseppe; Mura, Raffaele; Scionis, Luca; Piras, Giorgio; Pintor, Maura; Demontis, Ambra; Biggio, Battista | - | Ciaco - i6doc.com |
Hardening RGB-D object recognition systems against adversarial patch attacks | 1-gen-2023 | Zheng, Yang; Demetrio, Luca; Cinà, Antonio Emanuele; Feng, Xiaoyi; Xia, Zhaoqiang; Jiang, Xiaoyue; Demontis, Ambra; Biggio, Battista; Roli, Fabio | INFORMATION SCIENCES | - |
Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning | 1-gen-2023 | Emanuele Cinà, Antonio; Grosse, Kathrin; Demontis, Ambra; Vascon, Sebastiano; Zellinger, Werner; Moser, Bernhard A.; Oprea, Alina; Biggio, Battista; Pelillo, Marcello; Roli, Fabio | ACM COMPUTING SURVEYS | - |
Minimizing Energy Consumption of Deep Learning Models by Energy-Aware Training | 1-gen-2023 | Lazzaro, Dario; Cinà, Antonio Emanuele; Pintor, Maura; Demontis, Ambra; Biggio, Battista; Roli, Fabio; Pelillo, Marcello | - | - |
Stateful detection of adversarial reprogramming | 1-gen-2023 | Zheng, Yang; Feng, Xiaoyi; Xia, Zhaoqiang; Jiang, Xiaoyue; Pintor, Maura; Demontis, Ambra; Biggio, Battista; Roli, Fabio | INFORMATION SCIENCES | - |
Cybersecurity and AI: The PRALab Research Experience | 1-gen-2023 | Pintor, Maura; Orru, Giulia; Maiorca, Davide; Demontis, Ambra; Demetrio, Luca; Marcialis, GIAN LUCA; Biggio, Battista; Roli, Fabio | - | CEUR-WS Team, Redaktion Sun SITE |
AI Security and Safety: The PRALab Research Experience | 1-gen-2023 | Demontis, Ambra; Pintor, Maura; Demetrio, Luca; Sotgiu, Angelo; Angioni, Daniele; Piras, Giorgio; Gupta, Srishti; Biggio, Battista; Roli, Fabio | - | CEUR-WS Team, Redaktion Sun SITE |
ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches | 1-gen-2023 | Pintor, Maura; Angioni, Daniele; Sotgiu, Angelo; Demetrio, Luca; Demontis, Ambra; Biggio, Battista; Roli, Fabio | PATTERN RECOGNITION | - |
Detecting Attacks Against Deep Reinforcement Learning for Autonomous Driving | 1-gen-2023 | Pintor, Maura; Demetrio, Luca; Sotgiu, Angelo; Lin, HSIAO-YING; Fang, Chengfang; Demontis, Ambra; Biggio, Battista | - | - |
Samples on Thin Ice: Re-evaluating Adversarial Pruning of Neural Networks | 1-gen-2023 | Piras, Giorgio; Pintor, Maura; Demontis, Ambra; Biggio, Battista | - | - |
Why adversarial reprogramming works, when it fails, and how to tell the difference | 1-gen-2023 | Zheng, Yang; Feng, Xiaoyi; Xia, Zhaoqiang; Jiang, Xiaoyue; Demontis, Ambra; Pintor, Maura; Biggio, Battista; Roli, Fabio | INFORMATION SCIENCES | - |
The Threat of Offensive AI to Organizations | 1-gen-2023 | Mirsky, Y.; Demontis, A.; Kotak, J.; Shankar, R.; Gelei, D.; Yang, L.; Zhang, X.; Pintor, M.; Lee, W.; Elovici, Y.; Biggio, B. | COMPUTERS & SECURITY | - |
Domain Knowledge Alleviates Adversarial Attacks in Multi-Label Classifiers | 1-gen-2022 | Melacci, S.; Ciravegna, G.; Sotgiu, A.; Demontis, A.; Biggio, B.; Gori, M.; Roli, F. | IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | - |
Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples | 1-gen-2022 | Pintor, Maura; Demetrio, Luca; Sotgiu, Angelo; Demontis, Ambra; Carlini, Nicholas; Biggio, Battista; Roli, Fabio | - | Neural information processing systems foundation |
A Hybrid Training-Time and Run-Time Defense Against Adversarial Attacks in Modulation Classification | 1-gen-2022 | Zhang, L; Lambotharan, S; Zheng, G; Liao, Gs; Demontis, A; Roli, F | IEEE WIRELESS COMMUNICATIONS LETTERS | - |
Do gradient-based explanations tell anything about adversarial robustness to android malware? | 1-gen-2022 | Melis, M.; Scalas, M.; Demontis, A.; Maiorca, D.; Biggio, B.; Giacinto, G.; Roli, F. | INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS | - |
secml: Secure and explainable machine learning in Python | 1-gen-2022 | Pintor, Maura; Demetrio, Luca; Sotgiu, Angelo; Melis, Marco; Demontis, Ambra; Biggio, Battista | SOFTWAREX | - |
The hammer and the nut: is bilevel optimization really needed to poison linear classifiers? | 1-gen-2021 | Cina, A. E.; Vascon, S.; Demontis, A.; Biggio, B.; Roli, F.; Pelillo, M. | - | IEEE, Institute of Electrical and Electronics Engineers |
Deep neural rejection against adversarial examples | 1-gen-2020 | Sotgiu, Angelo; Demontis, Ambra; Melis, Marco; Biggio, Battista; Fumera, Giorgio; Feng, Xiaoyi; Roli, Fabio | EURASIP JOURNAL ON MULTIMEDIA AND INFORMATION SECURITY | - |
Legenda icone
- file ad accesso aperto
- file disponibili sulla rete interna
- file disponibili agli utenti autorizzati
- file disponibili solo agli amministratori
- file sotto embargo
- nessun file disponibile