.png){kind=icon}
返回
An efficient adversarial example generation algorithm based on an accelerated gradient iterative fast gradient
.png){kind=icon}
PRE
AI
DOI：10.1016/j.csi.2021.103612.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Most existing deep neural networks are susceptible to the influence of adversarial examples, which may cause them to output incorrect prediction results. An adversarial example is the addition of small noise disturbances to the input data samples, which will deceive the classification. Generally, these modifications are very small noise disturbances, which are not easily noticed by the human eye. However, most existing adversarial attacks achieve only low success rates in typical black-box settings, where the attackers have no prior knowledge about the model structures and/or model parameters. To tackle this problem, we propose an iterative algorithm based on an acceleration gradient to enhance the adversary attack. Our method accumulates the gradient of the loss function in each iteration and uses the next gradient information to influence the future gradient. We also introduce the scaling invariance principle of a deep neural network to optimize the input images for black-box attacks. In addition, to handle the drawbacks of a traditional iterative fast gradient sign method, we further present two gradient optimization methods. Experimental results on the ImageNet dataset show that our attack methods can achieve good transferability. In addition, those models obtained by integrated adversarial training with strong defense capability are also quite vulnerable to our black-box attack.
Keyword:
Iterative fast gradient
Adversarial examples
Transferable
期刊
C
IF:
3.1
论文数:
2.3K
被引数:
2.0K
机构
引用论文
The minimum cost consensus model considering the implicit trust of opinions similarities in social network group decision-making社会网络群体决策中考虑意见相似性隐性信任的最小成本共识模型
OAAI
.png){kind=icon}
OAAI分享收藏Fabrication of porous hollow γ-Al2O3 nanofibers by facile electrospinning and its application for water remediation静电纺丝法制备多孔中空 γ-Al2O3纳米纤维及其在水体修复中的应用
PREAI
分享收藏Towards the integration of the agent-oriented modeling diversity with a powertype-based language面向agent的建模多样性与基于powertype的语言的集成
PREAI
分享收藏
查看更多内容