A
Aleksandar Makelov
Researcher at Massachusetts Institute of Technology
Publications - 3
Citations - 9370
Aleksandar Makelov is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Deep learning & Concrete security. The author has an hindex of 2, co-authored 2 publications receiving 6430 citations.
Papers
More filters
Posted Content
Towards Deep Learning Models Resistant to Adversarial Attacks
TL;DR: This work studies the adversarial robustness of neural networks through the lens of robust optimization, and suggests the notion of security against a first-order adversary as a natural and broad security guarantee.
Proceedings Article
Towards Deep Learning Models Resistant to Adversarial Attacks.
TL;DR: This article studied the adversarial robustness of neural networks through the lens of robust optimization and identified methods for both training and attacking neural networks that are reliable and, in a certain sense, universal.
Rethinking Backdoor Attacks
Alaa Khaddaj,Guillaume Leclerc,Aleksandar Makelov,Kristian Georgiev,Hadi Salman,Andrew Ilyas,Aleksander Madry +6 more
TL;DR: In this article , the authors show that without structural information about the training data distribution, backdoor attacks are indistinguishable from naturally-occurring features in the data and thus impossible to"detect" in a general sense.