.png){kind=icon}
返回
EGM: An Efficient Generative Model for Unrestricted Adversarial Examples
.png){kind=icon}
PRE
AI
DOI：10.1145/3511893.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Unrestricted adversarial examples allow the attacker to start attacks without given clean samples, which are quite aggressive and threatening. However, existing works for generating unrestricted adversary examples are quite inefficient and cannot achieve a high success rate. In this article, we explore an end-to-end and effective solution for unrestricted adversary example generation. To stabilize the training process and make our generative model converge to satisfactory results, we design a novel decoupled two-step efficient generative model (EGM), which contains a conditional reference generator and a conditional adversarial transformer. The former is responsible for generating reference samples from noises and source classes. The latter is responsible for converting the reference sample into adversarial examples corresponding to target classes. To improve the success rate, we design a new strategy, augmentation of adversarial labels to produce dynamic target labels and enhance the exploration ability of EGM. Such a strategy can be also applied to existing attacks to improve their attack success rates, which is of independent interest. We conduct extensive experiments to evaluate our proposed model and demonstrate the necessity of decoupling the generation process in EGM. Experimental results show our EGM is much faster and achieves a higher success rate than the state-of-the-art attacks.
Keyword:
Perturbation-based adversarial example
unrestricted adversarial example
efficiency
attack success rate
期刊
IF:
4.7
论文数:
1.0K
被引数:
2.0K
机构
引用论文
.png){kind=icon}
Welding characteristics of aluminum, copper, nickel and aluminum alloy with alumina coating using ultrasonic complex vibration welding equipments铝、铜、镍及铝合金氧化铝涂层超声复合振动焊接特性研究
PREAI
分享收藏
查看更多内容