MAWSEO: Adversarial Wiki Search Poisoning for Illicit Online Promotion
Zilong Lin, Zhengyi Li, Xiaojing Liao, XiaoFeng Wang, Xiaozhong Liu
摘要
As a prominent instance of vandalism edits, Wiki search poisoning for illicit promotion is a cybercrime in which the adversary aims at editing Wiki articles to promote illicit businesses through Wiki search results of relevant queries. In this paper, we report a study that, for the first time, shows that such stealthy blackhat SEO on Wiki can be automated. Our technique, called MAWSEO, employs adversarial revisions to achieve real-world cybercriminal objectives, including rank boosting, vandalism detection evasion, topic relevancy, semantic consistency, user awareness (but not alarming) of promotional content, etc. Our evaluation and user study demonstrate that MAWSEO is capable of effectively and efficiently generating adversarial vandalism edits, which can bypass state-of-the-art built-in Wiki vandalism detectors, and also get promotional content through to Wiki users without triggering their alarms. In addition, we investigated potential defense, including coherence based detection and adversarial training of vandalism detection, against our attack in the Wiki ecosystem.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper7
- ``Someone Hid It!'': Query-Agnostic Black-Box Attacks on LLM-Based RetrievalJiate Li, Defu Cao, Li Li, Wei Yang 等ICML 2026 · 被引用 4 次
- Imperceptible Content Poisoning in LLM-Powered ApplicationsQuan Zhang, Chijin Zhou, Gwihwan Go, Binqi Zeng 等ASE 2024 · 被引用 3 次
- Exposing the Hidden Layer: Software Repositories in the Service of Seo ManipulationMengying Wu, Geng Hong, Wuyuao Mai, Xinyi Wu 等ICSE 2025 · 被引用 1 次
- Into the Dark: Unveiling Internal Site Search Abused for Black Hat SEOYunyi Zhang, Mingxuan Liu, Baojun Liu, Yiming Zhang 等USENIX Security 2024 · 被引用 1 次
- FlippedRAG: Black-Box Opinion Manipulation Adversarial Attacks to Retrieval-Augmented Generation ModelsZhuo Chen, Yuyang Gong, Jiawei Liu, Miaokun Chen 等CCS 2025
它引用的顶会 Paper6
- TextBugger: Generating Adversarial Text Against Real-world ApplicationsJinfeng Li, Shouling Ji, Tianyu Du, Bo Li 等NDSS 2019 · 被引用 876 次
- ORES: Lowering Barriers with Participatory Machine Learning in WikipediaAaron Halfaker, R. Stuart GeigerCSCW 2020 · 被引用 84 次
- Seeking Nonsense, Looking for Trouble: Efficient Promotional-Infection Detection through Semantic Inconsistency SearchXiaojing Liao, Kan Yuan, XiaoFeng Wang, Zhongyu Pei 等S&P 2016 · 被引用 41 次
- Adversarial Semantic CollisionsCongzheng Song, Alexander M. Rush, Vitaly ShmatikovEMNLP 2020 · 被引用 31 次
- Order-Disorder: Imitation Adversarial Attacks for Black-box Neural Ranking ModelsJiawei Liu, Yangyang Kang, Di Tang, Kaisong Song 等CCS 2022 · 被引用 22 次
相关 Paper
- Scalable Detection of Promotional Website Defacements in Black Hat SEO CampaignsRonghai Yang, Xianbo Wang, Cheng Chi, Dawei Wang 等USENIX Security 2021 · 被引用 27 次
- Topic-oriented Adversarial Attacks against Black-box Neural Ranking ModelsYu-An Liu, Ruqing Zhang, Jiafeng Guo, Maarten de Rijke 等SIGIR 2023 · 被引用 20 次
- The Ever-Changing Labyrinth: A Large-Scale Analysis of Wildcard DNS Powered Blackhat SEOKun Du, Hao Yang, Zhou Li, Hai-Xin Duan 等USENIX Security 2016 · 被引用 40 次
- Unsupervised Corpus Poisoning Attacks in Continuous Space for Dense RetrievalYongkang Li, Panagiotis Eustratiadis, Simon Lupart, Evangelos KanoulasSIGIR 2025 · 被引用 3 次
- Measuring and Analyzing Search Engine Poisoning of Linguistic CollisionsMatthew Joslin, Neng Li, Shuang Hao, Minhui Xue 等S&P 2019 · 被引用 18 次
