.png){kind=icon}
返回
A Backdoor Attack Against LSTM-Based Text Classification Systems
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2019.2941376.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
With the widespread use of deep learning system in many applications, the adversary has strong incentive to explore vulnerabilities of deep neural networks and manipulate them. Backdoor attacks against deep neural networks have been reported to be a new type of threat. In this attack, the adversary will inject backdoors into the model and then cause the misbehavior of the model through inputs including backdoor triggers. Existed research mainly focuses on backdoor attacks in image classification based on CNN, little attention has been paid to the backdoor attacks in RNN. In this paper, we implement a backdoor attack against LSTM-based text classification by data poisoning. After the backdoor is injected, the model will misclassify any text samples that contains a specific trigger sentence into the target category determined by the adversary. The backdoor attack is stealthy and the backdoor injected in the model has little impact on the performance of the model. We consider the backdoor attack in black-box setting, where the adversary has no knowledge of model structures or training algorithms except for a small amount of training data. We verify the attack through sentiment analysis experiment on the dataset of IMDB movie reviews. The experimental results indicate that our attack can achieve around 96% success rate with 1% poisoning rate.
Keyword:
Backdoor attacks
LSTM
poisoning data
text classification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Cobalt and Copper Composite Oxides as Efficient Catalysts for Preferential Oxidation of CO in H2-Rich Stream钴和铜复合氧化物作为H2-Rich流中CO优先氧化的有效催化剂
PREAI
分享收藏Enhanced Performance of Solid Oxide Fuel Cell by Manipulating the Orientation of Cylindrical Pores in Anode Substrate.png)
Fuel Cells
Fuel CellsIF0
PREAI
分享收藏First-Principle Protocol for Calculating Ionization Energies and Redox Potentials of Solvated Molecules and Ions: Theory and Application to Aqueous Phenol and Phenolate计算溶剂化分子和离子的电离能和氧化还原电位的第一原理协议: 理论和对苯酚和酚盐水溶液的应用
OAAI
OAAI分享收藏ICT for informal workers in Sub-Saharan Africa: Systematic review and analysis撒哈拉以南非洲非正规工人的信通技术: 系统回顾和分析
PREAI
分享收藏Effects of Cooling Rate on Impact Toughness of an Ultrahigh-Strength TRIP-Aided Martensitic Steel
PREAI
分享收藏Categorical Perception of Speech by Children With Specific Language Impairments具有特定语言障碍的儿童对语音的分类感知OAAI
OAAI分享收藏
查看更多内容