I am a Computer Science Ph.D. Student at ETH Zürich, advised by Florian Tramèr. My interest is in how the current (and future) research about the security and privacy of machine learning systems can be applied to real-world systems. My aim is to understand what the threat models look like in the real-world, and, based on that, understand which attacks are feasible, and what defenses are most effective.
I earned a Computer Science M.Sc. at EPFL, with a strong focus on Machine Learning and Security, and a Computer Engineering B.Sc. at PoliTo. I did my Master thesis about the robustness of Vision Transformers supervised by Princeton University’s Prof. Mittal, and I am one of the co-authors and maintainers of RobustBench, a standardized benchmark for adversarial robustness.
I had internship experiences at Bloomberg LP, as an SWE intern, and at armasuisse CYD Campus, as a Research Intern, supervised by Prof. Humbert.
I attended Military Navy College “F. Morosini”, in Venice, I am a member of LeadTheFuture, the leading mentoring program for STEM students in Italy, and I have been junior entrepreneur at JEToP.
- Security and Privacy of Machine Learning in the real-world
Ph.D. in Computer Science, To begin in 8/2022
ETH Zürich - Swiss Federal Institute of Technology, Zürich, Switzerland 🇨🇭
M.Sc. in Computer Science, 2019 - 2022
EPFL - Swiss Federal Institute of Technology, Lausanne, Switzerland 🇨🇭
B.Sc. in Computer Engineering, 2016 - 2019
PoliTo - Politecnico di Torino, Italy 🇮🇹
Exchange Year, 2017 - 2018
Tongji University, Shanghai, China 🇨🇳
Recent News
[11/2022 - A Light Recipe to Train Robust Vision Transformers accepted at SaTML] The paper derived from my master thesis was accepted at the IEEE Conference on Secure and Trustworthy Machine Learning (SaTML). I’m looking forward to presenting my paper in February!
[09/2022 - New paper: A Light Recipe to Train Robust Vision Transformers] We uploaded on arXiv the paper derived from my Master’s thesis, with additional experiments and insights. Take a look here!
[08/2022 - I started my PhD] On August 1st, 2022, I started my PhD at ETH Zürich, in the Privacy and Security Lab of Prof. Florian Tramèr.
Recent Publications
Experience
(looking for more)
- Worked in the Multi Asset Risk System team, on the re‑design and implementation of the configuration of a distributed logging library.
Cyber-Defence Campus is the Swiss equivalent of DARPA,a research center of the ArmedForces for the cyber-defence capability development. I have been hosted and supervised by Dr. Humbert.
- Conducted research about Machine Unlearning and Membership Inference Attacks against Generative Models under the supervision of Dr. Mathias Humbert.
- Tools in use: PyTorch, PyTorch Lightning, Comet ML, and Python.
Reply is one of the top IT consulting groups in Italy, with revenue worth €1B+ in 2018. I have interned at Blue Reply, Reply’s company that offers IBM based solutions.
- Created a chatbot that answers questions about GDPR law. The bot could help 320M+ EU citizens to easily understand GDPR. Stack: TypeScript, Redis, MongoDB, IBM Watson Assistant, Docker.
- Worked on RPA, using Automation Anywhere and Python. One ofthe bots I created decreased the duration of a task by 88%, without requiring human intervention in it.
Executive Board member responsible for public relations and partnerships.
- While I was in charge, JEToP signed 8 new strategic partnerships.
- Past positions: IT Consultant, Fundraising & Partnership Assistant.
Awards
What I’ve done
(so far)
Say hi 👋
Feel free to contact me :)
- [email protected] (academic stuff)
- [email protected] (personal stuff)
- DM Me
- Check out some code