Filipe Condessa

Joined

May 2021

Names

Filipe Condessa (Preferred)

Emails

****@us.bosch.com (Confirmed)

,

****@condessa.net (Confirmed)

,

****@bny.com (Confirmed)

Personal Links

Career & Education History

Researcher

Bosch (bosch.com)

2018 – 2021

Postdoc

Carnegie Mellon University (cmu.edu)

2016 – 2018

PhD student

Carnegie Mellon University (cmu.edu)

2011 – 2016

Advisors, Relations & Conflicts

Postdoc Advisor

radu marculescu

2016 – 2018

PhD Advisor

jelena kovacevic

2011 – 2016

Expertise

Robust Deep Learning

2018 – 2021

Publications

A Curious Case of Remarkable Resilience to Gradient Attacks via Fully Convolutional and Differentiable Front End with a Skip Connection
Leonid Boytsov, Ameya Joshi, Filipe Condessa
- Accepted by TMLR
- Readers: Everyone
Leveraging Foundation Models to Improve Lightweight Clients in Federated Learning
Xidong Wu, Wan-Yi Lin, Devin Willmott, Filipe Condessa, Yufei Huang, Zhenzhen Li, Madan Ganesh
- FL@FM-NeurIPS’23 Poster
- Readers: Everyone
Smooth-Reduce: Leveraging Patches for Improved Certified Robustness
Ameya Joshi, Minh Pham, Minsu Cho, Leonid Boytsov, Filipe Condessa, J Zico Kolter, Chinmay Hegde
- 22 Sept 2022 (modified: 15 Jan 2026)
- ICLR 2023 Conference Withdrawn Submission
- Readers: Everyone
Empirical robustification of pre-trained classifiers
Mohammad Sadegh Norouzzadeh, Wan-Yi Lin, Leonid Boytsov, Leslie Rice, Huan Zhang, Filipe Condessa, J Zico Kolter
- Published: 21 Jun 2021, Last Modified: 05 May 2023
- ICML 2021 Workshop AML Poster
- Readers: Everyone

Co-Authors