Ambra Demontis

发表

Why Do Adversarial Attacks Transfer? Explaining Transferability of Evasion and Poisoning Attacks

Fabio Roli, Marco Melis, Cristina Nita-Rotaru, 2018, USENIX Security Symposium.

Session details: Session 2B: Machine Learning for Cybersecurity

Ambra Demontis, Ambra Demontis, 2021, AISec@CCS.

Do gradient-based explanations tell anything about adversarial robustness to android malware?

Fabio Roli, Marco Melis, Giorgio Giacinto, 2020, International Journal of Machine Learning and Cybernetics.

The Threat of Offensive AI to Organizations pdf

Yuval Elovici, Wenke Lee, Battista Biggio, 2021, Comput. Secur..

Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning

Antonio Emanuele Cina, F. Roli, Sebastiano Vascon, 2022, ArXiv.

Session details: Session 2: Malware Detection

Ambra Demontis, Ambra Demontis, 2020 .

Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions pdf

Fabio Roli, Marcello Pelillo, Battista Biggio, 2021, ArXiv.

Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples pdf

Fabio Roli, Battista Biggio, Nicholas Carlini, 2021, ArXiv.

The Hammer and the Nut: Is Bilevel Optimization Really Needed to Poison Linear Classifiers?

Fabio Roli, Marcello Pelillo, Sebastiano Vascon, 2021, 2021 International Joint Conference on Neural Networks (IJCNN).

Deep neural rejection against adversarial examples

G. Fumera, F. Roli, Xiaoyi Feng, 2019, EURASIP Journal on Information Security.

Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples

Nicholas Carlini, F. Roli, B. Biggio, 2021, NeurIPS.

secml: Secure and explainable machine learning in Python

B. Biggio, Marco Melis, Ambra Demontis, 2022, SoftwareX.

Domain Knowledge Alleviates Adversarial Attacks in Multi-Label Classifiers

F. Roli, M. Gori, B. Biggio, 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

Do gradient-based explanations tell anything about adversarial robustness to android malware?

F. Roli, B. Biggio, Davide Maiorca, 2021, International Journal of Machine Learning and Cybernetics.

Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization

Fabio Roli, Luis Muñoz-González, Emil C. Lupu, 2017, AISec@CCS.

On the Intriguing Connections of Regularization, Input Gradients and Transferability of Evasion and Poisoning Attacks pdf

Fabio Roli, Marco Melis, Cristina Nita-Rotaru, 2018, ArXiv.

Adversarial Malware Binaries: Evading Deep Learning for Malware Detection in Executables

Claudia Eckert, Fabio Roli, Giorgio Giacinto, 2018, 2018 26th European Signal Processing Conference (EUSIPCO).

Secure Kernel Machines against Evasion Attacks

Fabio Roli, Giorgio Fumera, Battista Biggio, 2016, AISec@CCS.

Why Adversarial Reprogramming Works, When It Fails, and How to Tell the Difference

F. Roli, Xiaoyi Feng, B. Biggio, 2021, Inf. Sci..

ImageNet-Patch: A Dataset for Benchmarking Machine Learning Robustness against Adversarial Patches

F. Roli, B. Biggio, Ambra Demontis, 2022, Pattern Recognit..

Machine Learning Security Against Data Poisoning: Are We There Yet?

F. Roli, M. Pelillo, B. Biggio, 2022, Computer.

Yes, Machine Learning Can Be More Secure! A Case Study on Android Malware Detection

Fabio Roli, Marco Melis, Konrad Rieck, 2017, IEEE Transactions on Dependable and Secure Computing.

Is Deep Learning Safe for Robot Vision? Adversarial Examples Against the iCub Humanoid

Gavin Brown, Fabio Roli, Marco Melis, 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

A Hybrid Training-Time and Run-Time Defense Against Adversarial Attacks in Modulation Classification

F. Roli, S. Lambotharan, G. Zheng, 2022, IEEE Wireless Communications Letters.

Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning

F. Roli, Sebastiano Vascon, M. Pelillo, 2022, ACM Comput. Surv..

Energy-Latency Attacks via Sponge Poisoning

F. Roli, M. Pelillo, B. Biggio, 2022, ArXiv.

Can Domain Knowledge Alleviate Adversarial Attacks in Multi-Label Classifiers?

F. Roli, M. Gori, B. Biggio, 2020, arXiv.org.

A Survey on Reinforcement Learning Security with Application to Autonomous Driving

F. Roli, B. Biggio, Kathrin Grosse, 2022, ArXiv.

Super-Sparse Learning in Similarity Spaces

Fabio Roli, Marco Melis, Giorgio Fumera, 2016, IEEE Computational Intelligence Magazine.

On Security and Sparsity of Linear Classifiers for Adversarial Settings pdf

Fabio Roli, Giorgio Fumera, Battista Biggio, 2016, S+SSPR.

secml: A Python Library for Secure and Explainable Machine Learning pdf

Marco Melis, Battista Biggio, Ambra Demontis, 2019, ArXiv.

Backdoor Learning Curves: Explaining Backdoor Poisoning Beyond Influence Functions

F. Roli, M. Pelillo, B. Biggio, 2021, ArXiv.

Infinity-Norm Support Vector Machines Against Adversarial Label Contamination

Fabio Roli, Giorgio Fumera, Giorgio Giacinto, 2017, ITASEC.

Minimizing Energy Consumption of Deep Learning Models by Energy-Aware Training

F. Roli, M. Pelillo, B. Biggio, 2023, ICIAP.

Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples

Nicholas Carlini, F. Roli, B. Biggio, 2021, NeurIPS.

Samples on Thin Ice: Re-Evaluating Adversarial Pruning of Neural Networks

B. Biggio, Ambra Demontis, Maura Pintor, 2023, International Conference on Machine Learning and Computing.