Blockchain-Assisted Unsupervised Learning Method for Crowdsourcing Reputation Management

Crowdsourcing holds broad applications in information acquisition and dissemination,yet encounters challenges pertaining to data quality assessment and user reputation management.Reputation mechanisms stand as crucial solutions for appraising and updating participant reputation scores,thereby elevating the quality and dependability of crowdsourced data.However,these mechanisms face several challenges in traditional crowdsourcing systems:1)platform security lacks robust guarantees and may be susceptible to attacks;2)there exists a potential for large-scale privacy breaches;and 3)incentive mechanisms relying on reputation scores may encounter issues as reputation updates hinge on task demander evaluations,occasionally lacking a dedicated reputation update module.This paper introduces a reputation update scheme tailored for crowdsourcing,with a focus on proficiently overseeing participant reputations and alleviating the impact of malicious activities on the sensing system.Here,the reputation update scheme is determined by an Empirical Cumulative distribution-based Outlier Detection method(ECOD).Our scheme embraces a blockchain-based crowdsourcing framework utilizing a homomorphic encryption method to ensure data transparency and tamper-resistance.Computation of user reputation scores relies on their behavioral history,actively discouraging undesirable conduct.Additionally,we introduce a dynamic weight incentive mechanism that mirrors alterations in participant reputation,enabling the system to allocate incentives based on user behavior and reputation.Our scheme undergoes evaluation on 11 datasets,revealing substantial enhancements in data credibility for crowdsourcing systems and a reduction in the influence of malicious behavior.This research not only presents a practical solution for crowdsourcing reputation management but also offers valuable insights for future research and applications,holding promise for fostering more reliable and high-quality data collection in crowdsourcing across diverse domains.

N-gram MalGAN:Evading machine learning detection via feature n-gram

In recent years,many adversarial malware examples with different feature strategies,especially GAN and its variants,have been introduced to handle the security threats,e.g.,evading the detection of machine learning detectors.However,these solutions still suffer from problems of complicated deployment or long running time.In this paper,we propose an n-gram MalGAN method to solve these problems.We borrow the idea of n-gram from the Natural Language Processing(NLP)area to expand feature sources for adversarial malware examples in MalGAN.Generally,the n-gram MalGAN obtains the feature vector directly from the hexadecimal bytecodes of the executable file.It can be implemented easily and conveniently with a simple program language(e.g.,C++),with no need for any prior knowledge of the executable file or any professional feature extraction tools.These features are functionally independent and thus can be added to the non-functional area of the malicious program to maintain its original executability.In this way,the n-gram could make the adversarial attack easier and more convenient.Experimental results show that the evasion rate of the n-gram MalGAN is at least 88.58%to attack different machine learning algorithms under an appropriate group rate,growing to even 100%for the Random Forest algorithm.