Papers › ZeroGrad : Mitigating and Explaining Catastrophic Overfitting in FGSM Adversarial Training

ZeroGrad : Mitigating and Explaining Catastrophic Overfitting in FGSM Adversarial Training

29 Mar 2021arXiv:2103.15476archive 2025-07-28

Zeinab Golgooni, Mehrdad Saberi, Masih Eskandar, Mohammad Hossein Rohban

Making deep neural networks robust to small adversarial noises has recently been sought in many applications. Adversarial training through iterative projected gradient descent (PGD) has been established as one of the mainstream ideas to achieve this goal. However, PGD is computationally demanding and often prohibitive in case of large datasets and models. For this reason, single-step PGD, also known as FGSM, has recently gained interest in the field. Unfortunately, FGSM-training leads to a phenomenon called ``catastrophic overfitting," which is a sudden drop in the adversarial accuracy under the PGD attack. In this paper, we support the idea that small input gradients play a key role in this phenomenon, and hence propose to zero the input gradient elements that are small for crafting FGSM attacks. Our proposed idea, while being simple and efficient, achieves competitive adversarial accuracy on various datasets.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

rohban-lab/catastrophic_overfitting officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections