EXPERIENCE
| CARVIEW |
Select Language
HTTP/2 200
server: GitHub.com
content-type: text/html; charset=utf-8
last-modified: Tue, 09 Dec 2025 13:24:37 GMT
access-control-allow-origin: *
strict-transport-security: max-age=31556952
etag: W/"69382315-27ae"
expires: Tue, 30 Dec 2025 08:32:15 GMT
cache-control: max-age=600
content-encoding: gzip
x-proxy-cache: MISS
x-github-request-id: 5EB3:2D64E0:9C5786:AFB17E:69538BB7
accept-ranges: bytes
age: 0
date: Tue, 30 Dec 2025 08:22:15 GMT
via: 1.1 varnish
x-served-by: cache-bom-vanm7210092-BOM
x-cache: MISS
x-cache-hits: 0
x-timer: S1767082935.430333,VS0,VE227
vary: Accept-Encoding
x-fastly-request-id: e2b973cfad66de2ff8f9334a544e9ff795291484
content-length: 3336
Portfolio | Matteo Boglioni
-->
Matteo Boglioni
Computer Science MSc Student at ETH Zürich.
I’m particularly interested in red-teaming and model auditing as proactive techniques to uncover existing models’ vulnerabilities. I aim to assess and expose these flaws and inconsistencies, both in performance and security, to increase robustness and reliability towards distribution shifts, adversarial inputs, and unintended behaviors. I believe this step is crucial for a responsible and ethical deployment of AI.
RESEARCH INTERESTS
- Machine Learning Privacy and Security
- AI Safety
- LLMs Robustness and Generalization
- Privacy
HOBBIES
-
CLIMBING
75% -
ROAD CYCLING
90% -
VIDEOMAKING
60% -
TRAVELING & BACKPACKING
100%
RECENT PUBLICATIONS
[All Publications]-
Enhancing One-run Privacy Auditing with Quantile Regression-Based Membership InferenceIn Workshop on Theory and Practice of Differential Privacy, 2025
-
Optimizing Canaries for Privacy Auditing with Metagradient DescentBoglioni, Matteo, Liu, Terrance, Ilyas, Andrew, and Wu, Zhiwei Steven2025
-
Do Generalisation Results Generalise?Boglioni, Matteo, Sgobbi, Andrea, Tavernini, Gabriel, Rita, Francesco, Mosbach, Marius, and Pimentel, Tiago2025