Szegedy
A machine learning researcher recognized as one of the early systematic contributors to the concept of adversarial examples. In 2013, Szegedy published research demonstrating the vulnerability of deep neural networks to small perturbations in input data, laying foundational groundwork for subsequent adversarial robustness research.
Timeline (last 90 days)
The concept of adversarial examples was first systematically proposed by Szegedy and other researchers in 2013.
The concept of adversarial examples was first systematically articulated by Ian Goodfellow et al. in 2014, demonstrating that adding imperceptibly small perturbations to images in the computer vision domain can cause classifiers to produce incorrect judgments.
The adversarial attack phenomenon was first discovered by Szegedy et al. in 2013, after which Goodfellow et al. proposed classic attack methods such as FGSM.
All Facts (3)
The concept of adversarial examples was first systematically articulated by Ian Goodfellow et al. in 2014, demonstrating that adding imperceptibly small perturbations to images in the computer vision domain can cause classifiers to produce incorrect judgments.
70%UnverifiedThe concept of adversarial examples was first systematically proposed by Szegedy and other researchers in 2013.
50%UnverifiedThe adversarial attack phenomenon was first discovered by Szegedy et al. in 2013, after which Goodfellow et al. proposed classic attack methods such as FGSM.
50%