基于模型间迁移性的黑盒对抗攻击起点提升方法

Black Box Adversarial Attack Starting Point Promotion Method Based on Mobility Between Models

为高效地寻找基于决策的黑盒攻击下的对抗样本,提出一种利用模型之间的迁移性提升对抗起点的方法。通过模型之间的迁移性来循环叠加干扰图像,生成初始样本作为新的攻击起点进行边界攻击,实现基于决策的无目标黑盒对抗攻击和有目标黑盒对抗攻击。实验结果表明,无目标攻击节省了23%的查询次数,有目标攻击节省了17%的查询次数,且整个黑盒攻击算法所需时间低于原边界攻击算法所耗费的时间。

In order to efficiently find the adversarial samples under the decision-based black box attacks,a method using the mobility between models is proposed to enhance the adversarial starting point.The mobility is used to circularly superimpose interference images,and samples are generated as a new starting point for boundary attacks.Thus the decision making-based non-target adversarial black box attacks and targeted adversarial black box attacks are realized.Experimental results show that the query times required for the non-target attacks is reduced by 23%,and that required for the targeted attacks is reduced by 17%.Moreover,the whole black box attack algorithm takes less time than the original boundary attack algorithm.