The Art and Craft of Fraudulent App Promotion in Google Play

Rahman, Mohammad Ashiqur; Hernandez, Nestor; Recabarren, Ruben; Ahmed, Syed Ishtiaque; Cărbunar, Bogdan

doi:10.1145/3319535.3345658

Cited by 25 publications

(14 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Correspondingly, strategic spammers may carefully adjust the posting frequency to avoid traffic spikes [12]. Besides that, spammers could smooth out their reviews with moderate ratings (i.e., two or four stars out of five) to evade the detection [26]. To study the sensitivity of our algorithm on different behaviors of the spammer under promotion attack, we take the same setting in previous experiments, where all 5-star fake reviews are posted in one day, as a Weak Level Attack.…”

Section: Discussionmentioning

confidence: 99%

“…Online reviews and ratings contributed by real customers help shape reputations of the businesses and guide customer decisionmakings, playing an integrative role in e-commerce and websites such as Amazon [8], Yelp [21], and Google Play [26]. However, monetary incentives therein have also attracted a large number of spammers to hold sway over less informed customers: it is estimated that about 40% of the reviews on Amazon are fake (called "review spams") [33].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust Spammer Detection by Nash Reinforcement Learning

Dou¹,

Ma²,

Yu³

et al. 2020

Preprint

View full text Add to dashboard Cite

Online reviews provide product evaluations for customers to make decisions. Unfortunately, the evaluations can be manipulated using fake reviews ("spams") by professional spammers, who have learned increasingly insidious and powerful spamming strategies by adapting to the deployed detectors. Spamming strategies are hard to capture, as they can be varying quickly along time, different across spammers and target products, and more critically, remained unknown in most cases. Furthermore, most existing detectors focus on detection accuracy, which is not well-aligned with the goal of maintaining the trustworthiness of product evaluations. To address the challenges, we formulate a minimax game where the spammers and spam detectors compete with each other on their practical goals that are not solely based on detection accuracy. Nash equilibria of the game lead to stable detectors that are agnostic to any mixed detection strategies. However, the game has no closed-form solution and is not differentiable to admit the typical gradient-based algorithms. We turn the game into two dependent Markov Decision Processes (MDPs) to allow efficient stochastic optimization based on multi-armed bandit and policy gradient. We experiment on three large review datasets using various state-of-the-art spamming and detection strategies and show that the optimization algorithm can reliably find an equilibrial detector that can robustly and effectively prevent spammers with any mixed spamming strategies from attaining their practical goal. Our code is available at https://github.com/YingtongDou/Nash-Detect.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Robust Spammer Detection by Nash Reinforcement Learning

Dou¹,

Ma²,

Yu³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Our methodology reveals tasks aiming to manipulate app store metrics that are not publicly visible and not targeted at improving the app's standing in the app store, such as inflating in-app revenue or user engagement. Prior work has also interviewed fraudsters selling fake installs, reviews, and ratings in Google Play Store to reveal their operational characteristics [31,48]. While we do not directly interact with the people behind the incentivized install platforms, our work sheds light on the ecosystem at scale, and provides new insights into how these services operate, as well as how app developers may stand to benefit from using these services.…”

Section: Related Workmentioning

confidence: 99%

Understanding Incentivized Mobile App Installs on Google Play Store

Farooqi

Feal

Lauinger³

et al. 2020

Proceedings of the ACM Internet Measurement Conference

View full text Add to dashboard Cite

"Incentivized" advertising platforms allow mobile app developers to acquire new users by directly paying users to install and engage with mobile apps (e.g., create an account, make in-app purchases). Incentivized installs are banned by the Apple App Store and discouraged by the Google Play Store because they can manipulate app store metrics (e.g., install counts, appearance in top charts). Yet, many organizations still offer incentivized install services for Android apps. In this paper, we present the first study to understand the ecosystem of incentivized mobile app install campaigns in Android and its broader ramifications through a series of measurements. We identify incentivized install campaigns that require users to install an app and perform in-app tasks targeting manipulation of a wide variety of user engagement metrics (e.g., daily active users, user session lengths) and revenue. Our results suggest that these artificially inflated metrics can be effective in improving app store metrics as well as helping mobile app developers to attract funding from venture capitalists. Our study also indicates lax enforcement of the Google Play Store's existing policies to prevent these behaviors. It further motivates the need for stricter policing of incentivized install campaigns. Our proposed measurements can also be leveraged by the Google Play Store to identify potential policy violations.

show abstract

“…We consider the ASO organizations studied in [67], see Figure 2, that employ combinations of (1) ASO admins who organize and coordinate communities of workers, and act as intermediaries between developers and workers, (2) professional workers who use multiple devices and accounts dedicated to ASO work, and (3) organic workers who blend product promotion with personal activities from their devices and accounts. In the following we informally use the terms organic device and account, to denote devices and accounts used by organic workers.…”

Section: System Modelmentioning

confidence: 99%

“…In previous work, Farooqi et al [38] have shown that incentivized app install platforms (IIP) are able to provide thousands of installs that successfully evade Google defenses. Rahman et al [67] have reported a variety of detectionavoidance techniques employed by organizations that specialize in retention installs and fake reviews. Such techniques include crowdsourcing ASO work to organic workers, who use their personal devices to conceal ASO work among everyday activities.…”

Section: Introductionmentioning

confidence: 99%

RacketStore: Measurements of ASO Deception in Google Play via Mobile and App Usage

Hernandez,

Recabarren,

Carbunar

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Online app search optimization (ASO) platforms that provide bulk installs and fake reviews for paying app developers in order to fraudulently boost their search rank in app stores, were shown to employ diverse and complex strategies that successfully evade state-of-theart detection methods. In this paper we introduce RacketStore, a platform to collect data from Android devices of participating ASO providers and regular users, on their interactions with apps which they install from the Google Play Store. We present measurements from a study of 943 installs of RacketStore on 803 unique devices controlled by ASO providers and regular users, that consists of 58,362,249 data snapshots collected from these devices, the 12,341 apps installed on them and their 110,511,637 Google Play reviews. We reveal significant differences between ASO providers and regular users in terms of the number and types of user accounts registered on their devices, the number of apps they review, and the intervals between the installation times of apps and their review times. We leverage these insights to introduce features that model the usage of apps and devices, and show that they can train supervised learning algorithms to detect paid app installs and fake reviews with an F1-measure of 99.72% (AUC above 0.99), and detect devices controlled by ASO providers with an F1-measure of 95.29% (AUC = 0.95). We discuss the costs associated with evading detection by our classifiers and also the potential for app stores to use our approach to detect ASO work with privacy. CCS CONCEPTS• Security and privacy → Social network security and privacy; Social aspects of security and privacy;

show abstract

The Art and Craft of Fraudulent App Promotion in Google Play

Cited by 25 publications

References 35 publications

Robust Spammer Detection by Nash Reinforcement Learning

Robust Spammer Detection by Nash Reinforcement Learning

Understanding Incentivized Mobile App Installs on Google Play Store

RacketStore: Measurements of ASO Deception in Google Play via Mobile and App Usage

Contact Info

Product

Resources

About