Amir Rahmati
Open Menu
Close Menu
Bio
Teaching
Research
Current Students
Alumni
Prospective Students
Publications
Useful Links
Transferring Adversarial Robustness Through Robust Representation Matching
Pratik Vaishnavi
,
Kevin Eykholt
,
Amir Rahmati
August, 2022
Preprint
PDF
Code
Source Document
Venue
Type
1
Publication
In
USENIX Security Symposium (USENIX Sec)
ML Security
←
Ares: A System-Oriented Wargame Framework for Adversarial ML
May 26, 2022
On the Feasibility of Compressing Certifiably Robust Neural Networks
Dec 9, 2022
→