Výsledky vyhledávání

Report

A Survey on Transferability of Adversarial Examples across Deep Neural Networks

Autor: Gu, Jindong, Jia, Xiaojun, de Jorge, Pau, Yu, Wenqain, Liu, Xinwei, Ma, Avery, Xun, Yuan, Hu, Anjun, Khakzar, Ashkan, Li, Zhijiang, Cao, Xiaochun, Torr, Philip

The emergence of Deep Neural Networks (DNNs) has revolutionized various domains by enabling the resolution of complex tasks spanning image recognition, natural language processing, and scientific problem-solving. However, this progress has also broug

Externí odkaz: http://arxiv.org/abs/2310.17626

Zobrazit plný text záznamu

Akademický článek

Application and Cutting Machining of Double Disc Milling Cutter

Autor: Li Zhijiang

Publikováno v: Jixie chuandong, Vol 40, Pp 171-176 (2016)

The CNC milling machine has the advantages of simple movement and high efficiency in manufacturing large modulus cylindrical gear. In order to improve the processing efficiency of rough milling,a method based on the double disk milling cutter is prop

Externí odkaz: https://doaj.org/article/f41d6e6b9b8c4066b430b7a5c83125e4

Zobrazit plný text záznamu

Report

Reliable Evaluation of Adversarial Transferability

Autor: Yu, Wenqian, Gu, Jindong, Li, Zhijiang, Torr, Philip

Adversarial examples (AEs) with small adversarial perturbations can mislead deep neural networks (DNNs) into wrong predictions. The AEs created on one DNN can also fool another DNN. Over the last few years, the transferability of AEs has garnered sig

Externí odkaz: http://arxiv.org/abs/2306.08565

Zobrazit plný text záznamu