Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Mazdak Teymourian

Mazdak Teymourian

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

ML×1AI×1Vision×1

Frequent co-authors

Ramtin Moslemi1×
Farzan Rahmani1×
Mohammad Hossein Rohban1×

Research Timeline

2026
SORA: Free Second-Order Attacks in Fast Adversarial Training

The paper introduces SORA, an adaptive adversarial training method that dynamically adjusts perturbation sizes to prevent Catastrophic Overfitting, achieving state-of-the-art robustness and clean accuracy.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIcs.CVRecentMay 30, 2026

SORA: Free Second-Order Attacks in Fast Adversarial Training

Mazdak Teymourian, Ramtin Moslemi, Farzan Rahmani, Mohammad Hossein Rohban

The paper introduces SORA, an adaptive adversarial training method that dynamically adjusts perturbation sizes to prevent Catastrophic Overfitting, achieving state-of-the-art robustness and clean accu…

View →