Giorgio Severi
Boston, MA
I am a Senior AI Safety Researcher at Microsoft, with the AI Red Team. I received my PhD from Northeastern University, where I worked in the NDS2 lab, advised by professor Alina Oprea.
My main interest is in machine learning security and adversarial machine learning (breaking AI systems), especially when ML is applied to security sensitive environments. I am also interested in most aspects of AI safety.
news
| Jun 4, 2024 | Our new paper Phantom: General Trigger Attacks on Retrieval Augmented Language Generation is now available on ArXiv |
|---|---|
| Jan 15, 2024 | Our paper Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning was accepeted at ICLR 2024! |
| Dec 7, 2023 | I am presenting our paper Poisoning Network Flow Classifiers at the Annual Computer Security Applications Conference (ACSAC) |
| Jun 1, 2022 | I am returning to Microsoft as an intern in the AI Red Team this summer. |
| Jun 1, 2021 | I will join the Microsoft Azure Trustworthy Machine Learning team as an intern this summer. |
latest posts
| Mar 13, 2019 | Visualizing wine data using Choropleths and Linking |
|---|---|
| Mar 10, 2019 | Installing VizDoom emulator on CentOS |