PaperMetrixEvidence-aware discovery
EN
Interface language English EN العربية AR Türkçe TR
Create account
Researcher profile

Seyed-Mohsen Moosavi-Dezfooli

2 papers in the PaperMetrix corpus

Publications

Papers by this author

  1. Divide, Denoise, and Defend against Adversarial Attacks

    2018 · arXiv (Cornell University)

    Deep neural networks, although shown to be a successful class of machine learning algorithms, are known to be extremely unstable to adversarial perturbations. Improving the robustness of neural networks against these attacks is important, especially …

  2. Understanding Catastrophic Overfitting in Adversarial Training

    2021 · arXiv (Cornell University)

    Recently, FGSM adversarial training is found to be able to train a robust model which is comparable to the one trained by PGD but an order of magnitude faster. However, there is a failure mode …