Nameles: An intelligent system for Real-Time Filtering of Invalid Ad Traffic

Pastor, Antonio; Pärssinen, Matti; Callejo, Patricia; Vallina, Pelayo; Cuevas, Antonio; Kotila, Mikko; Azcorra, Arturo

doi:10.1145/3308558.3313601

Cited by 7 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are different reported forms of ad fraud: from basic attacks using bots to visit websites where ads are shown [13], [6] and even clicked [14], to more sophisticated attacks using malicious software-referred to as adware-that performs hidden visits to websites from a user's browser [15]. Given the lack of transparency, the fraud problem is not isolated to artificial traffic to untrustworthy publishers.…”

Section: B Lack Of Transparency and Fraud In Online Advertising 1) Pmentioning

confidence: 99%

“…Finally, we also provide a high-level introduction to digital signatures, which enable our protocol. DSP2 ad server (7) bid response (13) billing notice (8) ad response (9) ad response (10) ad response (8) win no�ce (11) ad request (12) ad delivery (7) bid response (8) loss no�ce FIGURE 1. Overview of the programmatic advertising ecosystem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Establishing Trust in Online Advertising With Signed Transactions

2021

Self Cite

View full text Add to dashboard Cite

Section: B Lack Of Transparency and Fraud In Online Advertising 1) Pmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Establishing Trust in Online Advertising With Signed Transactions

2021

Self Cite

View full text Add to dashboard Cite

“…Among the great number of bid requests in RTB, there are many useless impressions created by bots, called invalid ad traffic 8 [36]. Such invalid ad traffic cannot create any real value for the advertisers but only waste the budget.…”

Section: ) Cooperation With Fraud Detectionmentioning

confidence: 99%

“…Such invalid ad traffic cannot create any real value for the advertisers but only waste the budget. To prevent spending any budget on invalid ad traffic, there are plenty of researches to detect these fraud activities in RTB [37,38,39,36]. The proposed bidding strategy can cooperate with any fraud detector as follows.…”

Section: ) Cooperation With Fraud Detectionmentioning

confidence: 99%

An Expected Win Rate-Based Real Time Bidding Strategy for Branding Campaign by the Model-Free Reinforcement Learning Model

Shih

Tsai

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The bidding strategy plays the most important role to help the Demand Side Platforms (DSPs) making bidding decisions on a large number of bid requests in Real Time Bidding (RTB) to satisfy the different objectives of campaigns under the lifetime and budget constraints. In this paper, we focus on branding campaign whose objective is to obtain as many impressions as possible under the lifetime and budget constraints. To achieve the objectives of branding campaigns, we propose a novel expected win rate-based bidding strategy for branding campaign under the lifetime and budget constraints by utilizing a model-free reinforcement learning model. Specifically, to prevent missing good opportunities resulting from submitting extremely low bid prices, the concept of the base winning price is introduced to determine the lower bound of expected winning price. In addition, to obtain more impressions, the concept of the DSP-specified budget spending plan is proposed to determine the proper winning prices. The base expected win rate is then calculated based on the base winning price and the winning price determined by the DSPspecified budget spending plan. Since RTB is a dynamic environment, we propose a novel expected win ratebased bidding strategy named EWDQN which utilizes Deep Q Network (DQN) to dynamically determine the expected win rate according to the base expected win rate and the current status of the RTB market, and then determines the bid price according to the expected win rate. To the best of our knowledge, this is the first research applying the reinforcement learning technique on the bidding strategies for branding campaign. To measure the performance of EWDQN, several experiments are conducted on two real datasets. Experimental results show that EWDQN outperforms the-state-of-the-art bidding strategies for branding campaign in terms of the number of obtained impressions and CPM (cost per thousand impressions).

show abstract

“…Hence, the protocol is readily implementable in the current ecosystem without requiring any modification, lowering the entry barrier for its adoption significantly. We DSP2 ad server (7) bid response (13) billing notice (8) ad response (9) ad response (10) ad response (8) win no�ce (11) ad request (12) ad delivery (7) bid response (8) have implemented the protocol and made the code available through the following GitHub repositories [9], [10]. We assess the performance of Ads.chain through a thorough analysis in a lab environment that emulates a real ad delivery process.…”

Section: Introductionmentioning

confidence: 99%

Establishing Trust in Online Advertising with Signed Transactions

Pastor,

Cuevas,

Cuevas

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Programmatic advertising operates one of the most sophisticated and efficient service platforms on the Internet. However, the complexity of this ecosystem is the main cause of one of the most important problems in online advertising, the lack of transparency. This lack of transparency leads to subsequent problems such as advertising fraud, which causes billions of dollars in losses.In this paper we propose Ads.chain, a technological solution to the lack-of-transparency problem in programmatic advertising. Ads.chain extends the current effort of the IAB in providing traceability in online advertising through the Ads.txt and Ads.cert solutions, addressing the limitations of these techniques. Ads.chain is a communication protocol that provides end-to-end cryptographic traceability at the ad transaction level. It can be seamlessly embedded in ad-tags and the OpenRTB protocol, the de-facto standards for communications in online advertising, allowing an incremental adoption by the industry.We have implemented the protocol and made the code publicly available. We assess the performance of Ads.chain through a thorough analysis in a lab environment that emulates a real ad delivery process. The obtained results show that our protocol adds delays lower than 0.25 ms per ad space on the web page and a marginal delay of 0.8 ms on the intermediaries. These results confirm its impact on the user experience and the overall operation of the programmatic ad delivery process can be considered negligible.

show abstract

Nameles: An intelligent system for Real-Time Filtering of Invalid Ad Traffic

Cited by 7 publications

References 12 publications

Establishing Trust in Online Advertising With Signed Transactions

Establishing Trust in Online Advertising With Signed Transactions

An Expected Win Rate-Based Real Time Bidding Strategy for Branding Campaign by the Model-Free Reinforcement Learning Model

Establishing Trust in Online Advertising with Signed Transactions

Contact Info

Product

Resources

About