IEICE TRANSACTIONS on Information
Detecting and Understanding Online Advertising Fraud in the Wild
Summary :
While the online advertisement is widely used on the web and on mobile applications, the monetary damages by advertising frauds (ad frauds) have become a severe problem. Countermeasures against ad frauds are evaded since they rely on noticeable features (e.g., burstiness of ad requests) that attackers can easily change. We propose an ad-fraud-detection method that leverages robust features against attacker evasion. We designed novel features on the basis of the statistics observed in an ad network calculated from a large amount of ad requests from legitimate users, such as the popularity of publisher websites and the tendencies of client environments. We assume that attackers cannot know of or manipulate these statistics and that features extracted from fraudulent ad requests tend to be outliers. These features are used to construct a machine-learning model for detecting fraudulent ad requests. We evaluated our proposed method by using ad-request logs observed within an actual ad network. The results revealed that our designed features improved the recall rate by 10% and had about 100,000-160,000 fewer false negatives per day than conventional features based on the burstiness of ad requests. In addition, by evaluating detection performance with long-term dataset, we confirmed that the proposed method is robust against performance degradation over time. Finally, we applied our proposed method to a large dataset constructed on an ad network and found several characteristics of the latest ad frauds in the wild, for example, a large amount of fraudulent ad requests is sent from cloud servers.
- Publication
- IEICE TRANSACTIONS on Information Vol.E103-D No.7 pp.1512-1523
- Publication Date
- 2020/07/01
- Publicized
- 2020/03/24
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.2019ICP0008
- Type of Manuscript
- Special Section PAPER (Special Section on Information and Communication System Security)
- Category
- Network and System Security
Authors
Fumihiro KANEI
NTT Secure Platform Laboratories,Yokohama National University
Daiki CHIBA
NTT Secure Platform Laboratories
Kunio HATO
NTT Secure Platform Laboratories
Katsunari YOSHIOKA
Yokohama National University
Tsutomu MATSUMOTO
Yokohama National University
Mitsuaki AKIYAMA
NTT Secure Platform Laboratories
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Fumihiro KANEI, Daiki CHIBA, Kunio HATO, Katsunari YOSHIOKA, Tsutomu MATSUMOTO, Mitsuaki AKIYAMA, "Detecting and Understanding Online Advertising Fraud in the Wild" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 7, pp. 1512-1523, July 2020, doi: 10.1587/transinf.2019ICP0008.
Abstract: While the online advertisement is widely used on the web and on mobile applications, the monetary damages by advertising frauds (ad frauds) have become a severe problem. Countermeasures against ad frauds are evaded since they rely on noticeable features (e.g., burstiness of ad requests) that attackers can easily change. We propose an ad-fraud-detection method that leverages robust features against attacker evasion. We designed novel features on the basis of the statistics observed in an ad network calculated from a large amount of ad requests from legitimate users, such as the popularity of publisher websites and the tendencies of client environments. We assume that attackers cannot know of or manipulate these statistics and that features extracted from fraudulent ad requests tend to be outliers. These features are used to construct a machine-learning model for detecting fraudulent ad requests. We evaluated our proposed method by using ad-request logs observed within an actual ad network. The results revealed that our designed features improved the recall rate by 10% and had about 100,000-160,000 fewer false negatives per day than conventional features based on the burstiness of ad requests. In addition, by evaluating detection performance with long-term dataset, we confirmed that the proposed method is robust against performance degradation over time. Finally, we applied our proposed method to a large dataset constructed on an ad network and found several characteristics of the latest ad frauds in the wild, for example, a large amount of fraudulent ad requests is sent from cloud servers.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019ICP0008/_p
Copy
@ARTICLE{e103-d_7_1512,
author={Fumihiro KANEI, Daiki CHIBA, Kunio HATO, Katsunari YOSHIOKA, Tsutomu MATSUMOTO, Mitsuaki AKIYAMA, },
journal={IEICE TRANSACTIONS on Information},
title={Detecting and Understanding Online Advertising Fraud in the Wild},
year={2020},
volume={E103-D},
number={7},
pages={1512-1523},
abstract={While the online advertisement is widely used on the web and on mobile applications, the monetary damages by advertising frauds (ad frauds) have become a severe problem. Countermeasures against ad frauds are evaded since they rely on noticeable features (e.g., burstiness of ad requests) that attackers can easily change. We propose an ad-fraud-detection method that leverages robust features against attacker evasion. We designed novel features on the basis of the statistics observed in an ad network calculated from a large amount of ad requests from legitimate users, such as the popularity of publisher websites and the tendencies of client environments. We assume that attackers cannot know of or manipulate these statistics and that features extracted from fraudulent ad requests tend to be outliers. These features are used to construct a machine-learning model for detecting fraudulent ad requests. We evaluated our proposed method by using ad-request logs observed within an actual ad network. The results revealed that our designed features improved the recall rate by 10% and had about 100,000-160,000 fewer false negatives per day than conventional features based on the burstiness of ad requests. In addition, by evaluating detection performance with long-term dataset, we confirmed that the proposed method is robust against performance degradation over time. Finally, we applied our proposed method to a large dataset constructed on an ad network and found several characteristics of the latest ad frauds in the wild, for example, a large amount of fraudulent ad requests is sent from cloud servers.},
keywords={},
doi={10.1587/transinf.2019ICP0008},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - Detecting and Understanding Online Advertising Fraud in the Wild
T2 - IEICE TRANSACTIONS on Information
SP - 1512
EP - 1523
AU - Fumihiro KANEI
AU - Daiki CHIBA
AU - Kunio HATO
AU - Katsunari YOSHIOKA
AU - Tsutomu MATSUMOTO
AU - Mitsuaki AKIYAMA
PY - 2020
DO - 10.1587/transinf.2019ICP0008
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2020
AB - While the online advertisement is widely used on the web and on mobile applications, the monetary damages by advertising frauds (ad frauds) have become a severe problem. Countermeasures against ad frauds are evaded since they rely on noticeable features (e.g., burstiness of ad requests) that attackers can easily change. We propose an ad-fraud-detection method that leverages robust features against attacker evasion. We designed novel features on the basis of the statistics observed in an ad network calculated from a large amount of ad requests from legitimate users, such as the popularity of publisher websites and the tendencies of client environments. We assume that attackers cannot know of or manipulate these statistics and that features extracted from fraudulent ad requests tend to be outliers. These features are used to construct a machine-learning model for detecting fraudulent ad requests. We evaluated our proposed method by using ad-request logs observed within an actual ad network. The results revealed that our designed features improved the recall rate by 10% and had about 100,000-160,000 fewer false negatives per day than conventional features based on the burstiness of ad requests. In addition, by evaluating detection performance with long-term dataset, we confirmed that the proposed method is robust against performance degradation over time. Finally, we applied our proposed method to a large dataset constructed on an ad network and found several characteristics of the latest ad frauds in the wild, for example, a large amount of fraudulent ad requests is sent from cloud servers.
ER -
English
