Delving into Transferable Adversarial Examples and Black-box Attacks · HackerPapers discussions

Delving into Transferable Adversarial Examples and Black-box Attacks — mentioned by Imnimo

Sun, 21 Feb 2021 00:43:21 GMT

Transfer of adversarial perturbations between models is one of the main avenues of "black box" (where you don't know the target model's weights) attacks. Perturbations don't translate between models 100% of the time or anything, but many attacks are surprisingly transferable. There are also methods to make perturbations more transferable, for example by finding an attack that is effective against an ensemble of models, you increase the chances that it will transfer to an unseen model. https://arxiv.org/pdf/1611.02770.pdf

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

Delving into Transferable Adversarial Examples and Black-box Attacks — 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.