CV

Maura Pintor - Assistant Professor @ University of Cagliari and Collaborator @ Pluribus One.

Download pdf version

Last update: Sept. 3rd 2023

Education and Research

03/2023 - ongoing: Assistant Professor (RTDa)
University of Cagliari (Italy)
Duties included: Research on machine learning security.
10/2021 - 02/2022: Postdoctoral Researcher
- University of Cagliari (Italy)
- Duties included: Research on machine learning security.
2022 - Ph.D in Electronic and Computer Engineering, University of Cagliari (Italy)
- Visiting student at Eberhard Karls Universität Tübingen, March 2020 - June 2020
- Visiting student at Software Competence Center Hagenberg (SCCH), virtual, May 2021 - August 2021
- PhD Thesis: “Towards Debugging and Improving Adversarial Robustness Evaluations”
2018 - M.S. in Telecommunications Engineering, University of Cagliari (Italy)
2016 - B.S. in Electronic Engineering, University of Cagliari (Italy).

Work experience

03/2021 - 03/2022 : Collaborator for EU project
- Pluribus One S.r.l., Cagliari (Italy)
- Duties included: Collaboration for WP6 “Impact: Benchmark Datasets and Tool Flow Pilots” in the EU Project AssureMOSS.
03/2019 - 03/2020 : Collaborator for EU project
- Pluribus One S.r.l., Cagliari (Italy)
- Duties included: Design and integration of tools for evaluating machine learning robustness in the EU Project ALOHA.
02/2018 - 07/2018 : Software developer
- Pluribus One S.r.l., Cagliari (Italy)
- Duties included: Development of systems for internet traffic security.
07/2017 - 12/2017 : Collaborator at University of Cagliari
- University of Cagliari (Italy)
- Duties included: Project MIUR - Smart Cities - Cagliari Port 2020. Hardware and software design and implementation of IoT systems for data gathering and visualization. Software development for Linux OS based microprocessor (Raspberry Pi), sensor integration, data management and cloud storage.

Projects

10/2022 - ongoing: Participation, with the University of Cagliari, in the EU project ``European Lighthouse on Secure and Safe AI’’ (ELSA), Grant Agreement no.: 101070617, funded by the European Union in the programme HORIZON-CL4-2021-HUMAN-01.
10/2021 - ongoing : Participation, with the University of Cagliari, in the research project ``Huawei R\&D Agreement: Deep Reinforcement Learning Key Security Technologies’’, Grant Agreement n. TC20201118006.
03/2021 - ongoing: Scientific Coordinator, with the company Pluribus One, of the WP6 (Impact: Benchmark Datasets and Tool Flow Pilots) of the EU project ``Assurance and certification in secure Multi-party Open Software and Services’’ (AssureMOSS), Grant Agreement no.: 952647, funded by the EU Union in the programme H2020-SU-ICT-2019.
03/2019 - 03/2020: Scientific Coordinator, with the company Pluribus One, in the EU project ``Software framework for runtime-Adaptive and secure deep Learning On Heterogeneous Architectures’’ (ALOHA), Grant Agreement no.: 780788, funded by the EU Union in the programme H2020-ICT-2017-1.

Teaching

Teaching Assistant

10/2022 - ongoing : Teaching Assistant
- University of Cagliari (Italy)
- Duties included: Teaching Assistant for Machine Learning Security Course.
- MSc in Computer Engineering, Cybersecurity and Artificial Intelligence
09/2022 - ongoing : Teaching Assistant
- University of Cagliari (Italy)
- Duties included: Teaching Assistant for Machine Learning Security Course.
- PhD course, PhD programme in Information Engineering and Science, Univ. of Siena, PhD programme in Electronic and Computer Engineering, Univ. of Cagliari
05/2019 - ongoing : Teaching Assistant
- University of Cagliari (Italy)
- Duties included: Teaching Assistant for Machine Learning Course.
- MSc in Computer Engineering, Cybersecurity and Artificial Intelligence
12/2019 - ongoing : Teaching Assistant
- University of Cagliari (Italy)
- Duties included: Teaching Assistant for Industrial Software Development Course.
- MSc in Computer Engineering, Cybersecurity and Artificial Intelligence

Tutoring

11/2022 - 02/2023 : Academic Tutor
- University of Cagliari (Italy)
- Duties included: Tutor for Industrial Software Development Course.
03/2021 - 07/2021 : Academic Tutor
- University of Cagliari (Italy)
- Duties included: Tutor for Machine Learning Course.
02/2017 - 06/2018 : Academic Tutor
- University of Cagliari (Italy)
- Duties included: Tutor for Computer Science course, Python language.

Publications

Why adversarial reprogramming works, when it fails, and how to tell the difference

Yang Zheng, Xiaoyi Feng, Zhaoqiang Xia, Xiaoyue Jiang, Ambra Demontis, Maura Pintor, Battista Biggio, Fabio Roli, "Why adversarial reprogramming works, when it fails, and how to tell the difference." Information Sciences, 2023.

Stateful Detection of Adversarial Reprogramming

Yang Zheng, Xiaoyi Feng, Zhaoqiang Xia, Xiaoyue Jiang, Maura Pintor, Ambra Demontis, Battista Biggio, Fabio Roli, "Stateful Detection of Adversarial Reprogramming." Information Sciences, 2023.

ImageNet-Patch: A dataset for benchmarking machine learning robustness against adversarial patches

Maura Pintor, Daniele Angioni, Angelo Sotgiu, Luca Demetrio, Ambra Demontis, Battista Biggio, Fabio Roli, "ImageNet-Patch: A dataset for benchmarking machine learning robustness against adversarial patches." Pattern Recognition, 2023.

secml: Secure and explainable machine learning in Python

Maura Pintor, Luca Demetrio, Angelo Sotgiu, Marco Melis, Ambra Demontis, Battista Biggio, "secml: Secure and explainable machine learning in Python." SoftwareX, 2022.

Towards Debugging and Improving Adversarial Robustness Evaluations

Maura Pintor, "Towards Debugging and Improving Adversarial Robustness Evaluations." UNICA, 2022.

The threat of offensive ai to organizations

Yisroel Mirsky, Ambra Demontis, Jaidip Kotak, Ram Shankar, Deng Gelei, Liu Yang, Xiangyu Zhang, Maura Pintor, Wenke Lee, Yuval Elovici, Battista Biggio, "The threat of offensive ai to organizations." Computers & Security, 2022.

Robust Machine Learning for Malware Detection over Time

Daniele Angioni, Luca Demetrio, Maura Pintor, Battista Biggio, "Robust Machine Learning for Malware Detection over Time." In the proceedings of Proceedings of the Italian Conference on Cybersecurity (ITASEC 2022), Rome, Italy, June 20-23, 2022, 2022.

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

Maura Pintor, Luca Demetrio, Angelo Sotgiu, Giovanni Manca, Ambra Demontis, Nicholas Carlini, Battista Biggio, Fabio Roli, "Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples." In the proceedings of Advances in Neural Information Processing Systems, 2022.

Explaining Machine Learning DGA Detectors from DNS Traffic Data

Giorgio Piras, Maura Pintor, Luca Demetrio, Battista Biggio, "Explaining Machine Learning DGA Detectors from DNS Traffic Data." In the proceedings of Proceedings of the Italian Conference on Cybersecurity (ITASEC 2022), Rome, Italy, June 20-23, 2022, 2022.

A Survey on Reinforcement Learning Security with Application to Autonomous Driving

Ambra Demontis, Maura Pintor, Luca Demetrio, Kathrin Grosse, Hsiao-Ying Lin, Chengfang Fang, Battista Biggio, Fabio Roli, "A Survey on Reinforcement Learning Security with Application to Autonomous Driving." arXiv preprint arXiv:2212.06123, 2022.

Task-Specific Automation in Deep Learning Processes

Georg Buchgeher, Gerald Czech, Adriano Ribeiro, Werner Kloihofer, Paolo Meloni, Paola Busia, Gianfranco Deriu, Maura Pintor, Battista Biggio, Cristina Chesta, Luca Rinelli, David Solans, Manuel Portela, "Task-Specific Automation in Deep Learning Processes." In the proceedings of Database and Expert Systems Applications - DEXA 2021 Workshops, 2021.

Slope: A First-order Approach for Measuring Gradient Obfuscation

Maura Pintor, Luca Demetrio, Giovanni Manca, Battista Biggio, Fabio Roli, "Slope: A First-order Approach for Measuring Gradient Obfuscation." In the proceedings of ESANN 2021 - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 2021.

Fast minimum-norm adversarial attacks through adaptive norm constraints

Maura Pintor, Fabio Roli, Wieland Brendel, Battista Biggio, "Fast minimum-norm adversarial attacks through adaptive norm constraints." In the proceedings of Advances in Neural Information Processing Systems, 2021.

Evaluating adversarial attacks on ImageNet: A reality check on misclassification classes

Utku Ozbulak, M Pintor, Arnout Van, Wesley De, "Evaluating adversarial attacks on ImageNet: A reality check on misclassification classes." In the proceedings of NeurIPS2021, 35th Conference on Neural Information Processing Systems (NeurIPS 2021), Workshop on ImageNet: Past, Present, and Future, 2021.

Detecting Anomalies from Video-Sequences: a Novel Descriptor

Giulia Orrù, Davide Ghiani, Maura Pintor, Gian Marcialis, Fabio Roli, "Detecting Anomalies from Video-Sequences: a Novel Descriptor." In the proceedings of 25th International Conference on Pattern Recognition (ICPR 2020), 2020.

Why do adversarial attacks transfer? explaining transferability of evasion and poisoning attacks

Ambra Demontis, Marco Melis, Maura Pintor, Matthew Jagielski, Battista Biggio, Alina Oprea, Cristina Nita-Rotaru, Fabio Roli, "Why do adversarial attacks transfer? explaining transferability of evasion and poisoning attacks." In the proceedings of 28th USENIX security symposium (USENIX security 19), 2019.

Optimization and Deployment of CNNs at the Edge: The ALOHA Experience

Paolo Meloni, Daniela Loi, Paola Busia, Gianfranco Deriu, Andy Pimentel, Dolly Sapra, Todor Stefanov, Svetlana Minakova, Francesco Conti, Luca Benini, Maura Pintor, Battista Biggio, Bernhard Moser, Natalia Shepeleva, Nikos Fragoulis, Ilias Theodorakopoulos, Michael Masin, Francesca Palumbo, "Optimization and Deployment of CNNs at the Edge: The ALOHA Experience." In the proceedings of Proceedings of the 16th ACM International Conference on Computing Frontiers, 2019.

Be Right Beach: A Social IoT system for sustainable tourism based on beach overcrowding avoidance

Roberto Girau, Enrico Ferrara, Maura Pintor, Mariella Sole, Daniele Giusto, "Be Right Beach: A Social IoT system for sustainable tourism based on beach overcrowding avoidance." In the proceedings of 2018 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), 2018.

Architecture-aware design and implementation of CNN algorithms for embedded inference: the ALOHA project

Paolo Meloni, Daniela Loi, Gianfranco Deriu, Andy Pimentel, Dolly Sapra, Maura Pintor, Battista Biggio, Oscar Ripolles, David Solans, Francesco Conti, Luca Benini, Todor Stefanov, Svetlana Minakova, Bernhard Moser, Natalia Shepeleva, Michael Masin, Francesca Palumbo, Nikos Fragoulis, Ilias Theodorakopoulos, "Architecture-aware design and implementation of CNN algorithms for embedded inference: the ALOHA project." In the proceedings of 2018 30th International Conference on Microelectronics (ICM), 2018.

ALOHA: An Architectural-Aware Framework for Deep Learning at the Edge

P. Meloni, D. Loi, G. Deriu, A. Pimentel, D. Sapra, B. Moser, N. Shepeleva, F. Conti, L. Benini, O. Ripolles, D. Solans, Maura Pintor, B. Biggio, T. Stefanov, S. Minakova, N. Fragoulis, I. Theodorakopoulos, M. Masin, F. Palumbo, "ALOHA: An Architectural-Aware Framework for Deep Learning at the Edge." In the proceedings of Proceedings of the Workshop on INTelligent Embedded Systems Architectures and Applications, 2018.

Awards and accomplishments

06/2017 Best IoT - Week Hackathon Project - Siemens Award
- 1st place
- Project: Be Right Beach
- Sustainable tourism development, safety improvement, environment preservation and economic growth. Design and implementation of a system composed by two connected stations that provide sensor values and an important real-time analysis about the crowdedness.
- Link to the article
- Report

Other Activities

Conference and Workshop Chair

04/2024: Track co-chair at Safe, Secure and Robust AI Track at the SAC24 Conference
11/2023: Wokshop co-chair at 16th ACM Workshop on Artificial Intelligence and Security (AISec 2023), co-located with ACM CCS.
10/2023: Track co-chair of ESANN 2023 special session Towards Machine Learning Models that We Can Trust: Testing, Improving, and Explaining Robustness.
08/2022: Workshop co-chair at ARES International Workshop on Continuous Software Evaluation and Certification (IWCSEC 2022)
06/2022: Workshop co-chair at ITASEC AI for Security and Security of AI Workshop (AISSAI 2022)

Reviewer

Journals

IEEE Transactions on Information Forensics and Security (IEEE T-IFS)
IEEE Transactions on Image Processing (IEEE TIP)
IEEE Transactions on Dependable and Secure Computing (IEEE TDSC)
IEEE Transactions on Neural Networks and Learning Systems (IEEE-TNNLS)
ACM Transactions on Privacy and Security (TOPS)
Journal of Intelligent Information Systems (JIIS)
Eurasip Journal on Information Security
Machine Vision and Applications (MVAP)

Conferences

10/2023 PC at Twelfth International Conference on Learning Representations
05/2023 PC at Neural Information Processing Systems (NeurIPS 2023)
05/2023 PC at Annual Computer Security Applications Conference (ACSAC)
04/2023 PC at International Conference on Computer Vision(ICCV 2023)
03/2023 PC at the International Conference on Availability, Reliability and Security (ARES 2023)

Workshops

03/2023 PC at AAAI Workshop on Practical Deep Learning in the Wild
03/2023 PC at Euro S&P Workshop on Robust Malware Analysis
02/2023 PC at CVPR Workshop on Generative Models for Computer Vision
02/2023 PC at CVPR Workshop of Adversarial Machine Learning on Computer Vision: Art of Robustness
2022/04 Program Committee at ICML 2022 Workshop Shift happens: Crowdsourcing metrics and test datasets beyond ImageNet
2022/03 Program Committee at ICML 2022 Workshop on Socially Responsible Machine Learning
2021/08 Program Committee at 14th ACM CCS 2021 Workshop on Artificial Intelligence and Security (AISec)
2021/06 Program Committee at CVPR 2021 Workshop on Adversarial Machine Learning in Real-World Computer Vision Systems and Online Challenges
2021/06 Program Committee at ICML 2021 Workshop on Socially Responsible Machine Learning
2021/03 Program Committee at ICLR 2021 Workshop on Security and Safety in Machine Learning Systems
2020/11 Program Committee at AAAI 2021 Workshop - Towards Robust, Secure and Efficient Machine Learning
2020/08 Program Committee at ECCV 2020 Workshop on Adversarial Robustness in the Real World
2020/06 Program Committee at CVPR 2020 Workshop on Adversarial Machine Learning in Computer Vision

Talks and Posters

2023/07 Presented “Towards Machine Learning Models that We Can Trust: Hacking and (properly) Testing AI” at the ARTISAN Summer School 2023 (Role and effects of ARTificial Intelligence in Secure ApplicatioNs) in Vienna, Austria.
2023/05 Presented “Machine Learning Security: Lessons Learned and Future Challenges” at the Hamburg University of Technology (TUHH), Hamburg, Germany.
2022/11 Presented “Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples” at NeurIPS 2022
2022/06 Presented slides/video at ICML 2022 Workshop Shift happens: Crowdsourcing metrics and test datasets beyond ImageNet
2021/11 Presented slides/video at Cybersec&AI Connected (Slides)(Video)
2021/07 Poster Session at ICML 2021 Workshop A Blessing in Disguise: The Prospects and Perils of Adversarial Machine Learning (Poster)
2021/07 Oral talk at ICML 2021 Workshop A Blessing in Disguise: The Prospects and Perils of Adversarial Machine Learning (Video) (Poster)
2021/06 Poster Session at Microsoft Security Data Science Colloquium (Slides)
2019/10 Presented poster at Cybersec&AI Prague

Summer Schools (as a student)

2021/07 Regularization Methods for Machine Learning (RegML 2021)
2020/07 Machine Learning Summer School (MLSS 2020)
2019/07 International Computer Vision Summer School (ICVSS 2019)

Code

GitHub profile: https://github.com/maurapintor

SecML Library Maintainer
PandaVision Library Maintainer
MLSec Seminars Organizer of the series.