Empirical Evaluation and New Design for Fighting Evolving Twitter Spammers

By Chao Yang, Robert Chandler Harkreader, Guofei Gu. 2011

592 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Information Systems, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Information Systems

In Signal Processing

Citations in the corpus

Practical Evasion of a Learning-Based Classifier: A Case Study (2014, background): “From an adversarial viewpoint, the more information about a learning-based system is available, the higher the chances become that the system can be successfully gamed.”
Evading Classifiers by Morphing in the Dark (2017, background): “Evasion attacks against classifiers have been studied in numerous contexts [36, 23, 30, 35].”
The Paradigm-Shift of Social Spambots: Evidence, Theories, and Tools for the Arms Race (2017, methodology): “The traditional spambots #1 dataset is the training set used in [44], kindly provided to us by the authors of that work.”
Detection of Intrusions and Malware, and Vulnerability Assessment (2013, background): “Robustness of features is an important issue [37], and we can imagine that for some feature types, such as PE header information, could be more easily manipulated than others such as the system calls invoked in dynamic execution.”
Contextual Outlier Interpretation (2017, methodology): “According to [Yang et al., 2011], the robustness level varies for different attributes.”
SybilBlind: Detecting Fake Users in Online Social Networks without Manual Labels (2018, background): “Approaches in this direction [27,23,4,35,19,37,24,10,31,22] leverage various usergenerated contents (e.”
COMPA: Detecting Compromised Accounts on Social Networks (2013, background): “Thus, they are much more limited in their detection capabilities, and their approach mislabels fake profiles that try to be stealthy by sending legitimatelooking messages.”
Man vs. Machine: Practical Adversarial Detection of Malicious Crowdsourcing Workers (2014, background): “FFRatio, blacklisted URLs) or bot-like behaviors [4, 11, 42, 47, 50].”
Combating Attacks and Abuse in Large Online Communities (2016, background): “on spam detection [46, 213, 241], make it possible for adversaries to make reasonab le guesses on the feature space.”
Fake Twitter followers detection by denoising autoencoder (2017, methodology): “We based our feature set on the ones proposed in [30] and [22], as well as in various web sites 2 , and lately repeated in [8].”
CrowdTarget: Target-based Detection of Crowdturfing in Online Social Networks (2015, methodology): “First, detection methods based on account-based features [12,17,23,34,35] inspect the characteristic of individual account, e.”
A decade of social bot detection (2020, background): “between 2011 and 2013 provided the first evidence and the theoretical foundations to study social bot evolution [34].”
Analyzing spammers' social networks for fun and profit: a case study of cyber criminal ecosystem on twitter (2012, methodology): “Dataset I refers to the one with around half million accounts from our previous study [35].”
EVILCOHORT: Detecting Communities of Malicious Accounts on Online Services (2015, background): “On the other hand, E VIL C OHORT can detect an account (or an IP address) as malicious even if the account does not post any content on the online service.”
Fame for sale: Efficient detection of fake Twitter followers (2015, methodology): “To foster investigation on the novel issue of fake Twitter followers, our baseline dataset has been made publicly available for research purposes [33].”