Measurement and Detection Techniques for NFT Counterfeiting Fraud
With the boom in non-fungible tokens(NFT),security issues are becoming increas-ingly prominent,one of which is the phenomenon of NFT counterfeiting.In the decentralized environment,it becomes relatively easy to counterfeit other creators'NFT artworks,while it is very difficult to identify the authenticity,and identifying fakes and counterfeits requires a high level of blockchain technology background,The most prominent security problem of the current NFT is the threat of legitimacy due to the lack of regulation of NFT projects,and the NFT security problems of infringement,counterfeiting,plagiarism are difficult to solve only by the blockchain's own security mechanisms.In this paper,a systematic and in-depth research is conducted on measuring NFT counterfeiting and evaluating counterfeiting detection methods.A NFT counterfeiting threat model including the formal definition,counterfeiting process and counterfeiting features are established,NFT counterfeiting definition is given,NFT counterfeiting methods are analyzed,and a general NFT counterfeiting detection method is given.The smart contract addresses and historical trading data of 50 000 NFT projects on OpenSea,the largest NFT marketplace,were collected on a large scale,and the names,creation times,metadata,and digital payload of NFT images stored off-chain were collected from the Ethereum blockchain,from which 668 top NFT projects in terms of trading volume were selected to conduct measurements around the problem of NFT counterfeiting,and the results showed that 95 of them had been counterfeited 248 times,with the trading volume of more than $ 26 million,which is a clear indication of the seriousness of the counterfeiting and fraud problem facing the NFT ecosystem.Twenty-two image data augmentation methods were used to construct 5000 less perturbed attack test sample datasets,and the OpenSea online real-time counterfeit fraud detection system and the well-known third-party commercial detection platform Fnftf were tested for robustness through the black-box testing method.The test samples generated using the data augmentation method,the smaller the pertur-bation added,the better,but it is expected that the added perturbation can bypass the image similarity detection.Therefore,on the question of how to evaluate whether the test samples can deceive the visual judgment of NFT buyers,this paper evaluates the effectiveness of the test samples through Perceptual Hash Algorithm.The results of the tests showed that test samples of attacks constructed with six image data augmentation methods were able to easily bypass their counterfeit fraud detection system,and revealing the vulnerability of counterfeit fraud detection products in the NFT industry.In this paper,we address the problems of existing commercialized detection platforms in NFT counterfeit detection,such as poor robustness and vulnerability to bypass,a NFT image counterfeiting detection model is proposed and implemented,and the performance of the model is comparatively evaluated,and the AUC is improved by 15.9％compared to Fnftf,and then the inherent defects of image-based NFT counterfeit detection methods are discussed.Finally,the existing related literature has been thoroughly investigated to demonstrate that the research in this paper is a further refinement of the existing NFT fraud research results.
NETL
NSTL
万方数据
