Adapting Social Spam Infrastructure for Political Censorship

By Kurt Thomas, Chris Grier, Vern Paxson. 2012

96 citations recorded by the source corpus.

How researchers see this paper

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

Citations in the corpus

When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks (2018, methodology): “simulating an attacker who controls a network of accounts with well established statistics (e.g. number of followers). These accounts could originate either from black markets or compromised accounts [17, 43]. Our adversary uses these accounts to tweet about speciﬁc vulnerabilities. In our simulatio”
Exploiting Temporal Dynamics in Sybil Defenses (2015, background): “In December of 2011, a political protest by Russian citizens on the Twitter social network was swamped by spam from thousands of bot accounts [14, 22].”
Tweeting From Left to Right (2015, background): “In particular, the reason why we restrict our sample to users tweeting in two or more of our collections is that some spam bots are built so that they send automatic tweets that mention trending topics and popular hashtags in order to “hijack” them (Thomas et al., 2012).”
FeatureSmith: Automatically Engineering Features for Malware Detection by Mining the Security Literature (2016, background): “Ad-ditionally, anecdotal evidence suggests that adversaries may intentionally poison raw data [21, 48, 50], which results in a biased ground truth.”
Trafficking Fraudulent Accounts: The Role of the Underground Market in Twitter Spam and Abuse (2013, background): “We determine that merchants can provide thousands of accounts within 24 hours at a price of $0.02 – $0.10 per account.”
Misinformation in Social Media: Definition, Manipulation, and Detection (2019, methodology): “Though the method enables ground-truth data to be easily collected on a large scale, recent studies have also realized that the quality may be heavily influenced by community rules that are used to filter accounts [22; 41].”
SybilFuse: Combining Local Attributes with Global Structure to Perform Robust Sybil Detection (2018, background): “The attacker can leverage Sybil accounts to disrupt democratic election and inﬂuence ﬁnancial market via spreading fake news [4], [5], as well as compromise system security and privacy via propagating social malware, disseminating scams, and learning users’ private data [2], [3], [6]–[10].”