Countering Adversarial Images using Input Transformations — mentioned by Immortal333

Wed, 22 Jul 2020 15:55:36 GMT

This is tested on existing models/Face Recognition API which means locked pre-trained models. So, They might have learned way to add pixels such that model outputs very different embedding. This is know issue in deep learning [0][1][2]. I believe, Model trained on cloaked images would defeat its purpose and make this technique useless. [0] Su, Jiawei, Danilo Vasconcellos Vargas, and Kouichi Sakurai. "One pixel attack for fooling deep neural networks." IEEE Transactions on Evolutionary Computation 23.5 (2019): 828-841. [1] Guo, Chuan, et al. "Countering adversarial images using input…

Paper and discussion history. A mention is not an endorsement.

Countering Adversarial Images using Input Transformations — HN submission

Thu, 02 Nov 2017 16:09:33 GMT

Countering Adversarial Images Using Input Transformations [pdf]

11 points; 2 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Countering Adversarial Images using Input Transformations · HackerPapers discussions

Countering Adversarial Images using Input Transformations — mentioned by Immortal333

Countering Adversarial Images using Input Transformations — HN submission