Knowledge Commons of Institute of Automation,CAS
Towards Better Word Importance Ranking in Textual Adversarial Attacks | |
Shi, Jiahui1,2; Li, Linjing1,2; Zeng, Daniel Dajun1,2 | |
2023-08-02 | |
会议名称 | 2023 International Joint Conference on Neural Networks (IJCNN) |
会议日期 | June 18-23, 2023 |
会议地点 | Gold Coast, Australia |
出版者 | IEEE |
摘要 | Transformer models have been widely used in the filed of natural language processing due to their powerful learning ability. Nevertheless, recent studies have shown that transformer models are vulnerable to the maliciously crafted adversarial examples. In the challenging black box setting, main stream textual adversarial attacks typically consist of two steps: Word Importance Ranking (WIR) and word transformation. The attack performance is highly dependent on the ranking of words. Existing WIR methods are designed with heuristic rules, which lack theoretical guarantee and require a large amount of queries. To address this issue, we design a textual coalitional game and propose PWSHAP, which is a plug-and-in WIR method employing Shapley value to determine the significance of each word based on its impact on the classification. Through extensive experiments on three benchmark datasets and model architectures, we illustrate that the proposed PWSHAP achieve the-state-of-the-art attack success rate with significant fewer queries to the classification model. Meanwhile, the generated adversarial examples are more natural and coherent compared to the strong baselines. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 自然语言处理 |
国重实验室规划方向分类 | 语音语言处理 |
是否有论文关联数据集需要存交 | 否 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/52452 |
专题 | 多模态人工智能系统全国重点实验室_互联网大数据与信息安全 |
通讯作者 | Li, Linjing |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences |
第一作者单位 | 中国科学院自动化研究所 |
通讯作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Shi, Jiahui,Li, Linjing,Zeng, Daniel Dajun. Towards Better Word Importance Ranking in Textual Adversarial Attacks[C]:IEEE,2023. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Towards_Better_Word_(932KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论