Black-box Adversarial Attacks against Dense Retrieval Models: A Multi-view Contrastive Learning Method

Author:

Liu Yu-An1ORCID,Zhang Ruqing1ORCID,Guo Jiafeng1ORCID,de Rijke Maarten2ORCID,Chen Wei1ORCID,Fan Yixing1ORCID,Cheng Xueqi1ORCID

Affiliation:

1. ICT, CAS & University of Chinese Academy of Sciences, Beijing, China

2. University of Amsterdam, Amsterdam, Netherlands

Funder

Youth Innovation Promotion Association CAS

10-year program funded by the Dutch Ministry of Education

Innovation Project of ICT CAS

China Scholarship Council

CAS Project for Young Scientists in Basic Research

Lenovo-CAS Joint Lab Youth Scientist Project

National Natural Science Foundation of China (NSFC)

Proiect

LESSEN

Publisher

ACM

Reference56 articles.

1. Adversarial Web Search

2. Chegg. 2023. https://writing.chegg.com/. Chegg. 2023. https://writing.chegg.com/.

3. Xuanang Chen Ben He Zheng Ye Le Sun and Yingfei Sun. 2023. Towards Imperceptible Document Manipulations against Neural Ranking Models. In ACL. Xuanang Chen Ben He Zheng Ye Le Sun and Yingfei Sun. 2023. Towards Imperceptible Document Manipulations against Neural Ranking Models. In ACL.

4. Towards Robust Dense Retrieval via Local Ranking Alignment

5. Pengyu Cheng , Martin Renqiang Min , Dinghan Shen, Christopher Malon, Yizhe Zhang, Yitong Li, and Lawrence Carin. 2020 . Improving Disentangled Text Representation Learning with Information-Theoretic Guidance. In ACL. Pengyu Cheng, Martin Renqiang Min, Dinghan Shen, Christopher Malon, Yizhe Zhang, Yitong Li, and Lawrence Carin. 2020. Improving Disentangled Text Representation Learning with Information-Theoretic Guidance. In ACL.

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Robust Information Retrieval;Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval;2024-07-10

2. Are Large Language Models Good at Utility Judgments?;Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval;2024-07-10

3. Towards Robustness Analysis of E-Commerce Ranking System;Companion Proceedings of the ACM Web Conference 2024;2024-05-13

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3