FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1882350379> ?p ?o ?g. }

• W1882350379 endingPage "254" @default.
• W1882350379 startingPage "239" @default.
• W1882350379 abstract "Recent work in security and systems has embraced the use of machine learning (ML) techniques for identifying misbehavior, e.g. email spam and fake (Sybil) users in social networks. However, ML models are typically derived from fixed datasets, and must be periodically retrained. In adversarial environments, attackers can adapt by modifying their behavior or even sabotaging ML models by polluting training data.In this paper, we perform an empirical study of adversarial attacks against machine learning models in the context of detecting malicious crowdsourcing systems, where sites connect paying users with workers willing to carry out malicious campaigns. By using human workers, these systems can easily circumvent deployed security mechanisms, e.g. CAPTCHAs. We collect a dataset of malicious workers actively performing tasks on Weibo, China's Twitter, and use it to develop ML-based detectors. We show that traditional ML techniques are accurate (95%-99%) in detection but can be highly vulnerable to adversarial attacks, including simple evasion attacks (workers modify their behavior) and powerful poisoning attacks (where administrators tamper with the training set). We quantify the robustness of ML classifiers by evaluating them in a range of practical adversarial models using ground truth data. Our analysis provides a detailed look at practical adversarial attacks on ML models, and helps defenders make informed decisions in the design and configuration of ML detectors." @default.
• W1882350379 created "2016-06-24" @default.
• W1882350379 creator A5030921116 @default.
• W1882350379 creator A5051149614 @default.
• W1882350379 creator A5064821014 @default.
• W1882350379 creator A5085642649 @default.
• W1882350379 date "2014-08-20" @default.
• W1882350379 modified "2023-09-22" @default.
• W1882350379 title "Man vs. machine: practical adversarial detection of malicious crowdsourcing workers" @default.
• W1882350379 cites W1233141674 @default.
• W1882350379 cites W127585952 @default.
• W1882350379 cites W1512098439 @default.
• W1882350379 cites W1589713274 @default.
• W1882350379 cites W1604938182 @default.
• W1882350379 cites W1605925311 @default.
• W1882350379 cites W1730818938 @default.
• W1882350379 cites W1781642226 @default.
• W1882350379 cites W1912123407 @default.
• W1882350379 cites W1916595307 @default.
• W1882350379 cites W1965586806 @default.
• W1882350379 cites W1969568357 @default.
• W1882350379 cites W1977058264 @default.
• W1882350379 cites W1985987493 @default.
• W1882350379 cites W1986678144 @default.
• W1882350379 cites W2007562169 @default.
• W1882350379 cites W2014466911 @default.
• W1882350379 cites W2038296020 @default.
• W1882350379 cites W2045234005 @default.
• W1882350379 cites W2054888947 @default.
• W1882350379 cites W2095577883 @default.
• W1882350379 cites W2098395374 @default.
• W1882350379 cites W2108214308 @default.
• W1882350379 cites W2112507308 @default.
• W1882350379 cites W2118129996 @default.
• W1882350379 cites W2121761994 @default.
• W1882350379 cites W2125055259 @default.
• W1882350379 cites W2127935984 @default.
• W1882350379 cites W2128302979 @default.
• W1882350379 cites W2133990480 @default.
• W1882350379 cites W2137786570 @default.
• W1882350379 cites W2139144138 @default.
• W1882350379 cites W2151773168 @default.
• W1882350379 cites W2157578436 @default.
• W1882350379 cites W2161283199 @default.
• W1882350379 cites W2164441058 @default.
• W1882350379 cites W2165873170 @default.
• W1882350379 cites W2170112109 @default.
• W1882350379 cites W2293322640 @default.
• W1882350379 cites W2293768274 @default.
• W1882350379 cites W2435251607 @default.
• W1882350379 cites W2911964244 @default.
• W1882350379 cites W2949693138 @default.
• W1882350379 cites W2962974509 @default.
• W1882350379 cites W2962991180 @default.
• W1882350379 cites W2963817922 @default.
• W1882350379 cites W9223698 @default.
• W1882350379 cites W9657784 @default.
• W1882350379 hasPublicationYear "2014" @default.
• W1882350379 type Work @default.
• W1882350379 sameAs 1882350379 @default.
• W1882350379 citedByCount "47" @default.
• W1882350379 countsByYear W18823503792014 @default.
• W1882350379 countsByYear W18823503792015 @default.
• W1882350379 countsByYear W18823503792016 @default.
• W1882350379 countsByYear W18823503792017 @default.
• W1882350379 countsByYear W18823503792018 @default.
• W1882350379 countsByYear W18823503792019 @default.
• W1882350379 countsByYear W18823503792020 @default.
• W1882350379 countsByYear W18823503792021 @default.
• W1882350379 crossrefType "proceedings-article" @default.
• W1882350379 hasAuthorship W1882350379A5030921116 @default.
• W1882350379 hasAuthorship W1882350379A5051149614 @default.
• W1882350379 hasAuthorship W1882350379A5064821014 @default.
• W1882350379 hasAuthorship W1882350379A5085642649 @default.
• W1882350379 hasConcept C104317684 @default.
• W1882350379 hasConcept C119857082 @default.
• W1882350379 hasConcept C136764020 @default.
• W1882350379 hasConcept C146849305 @default.
• W1882350379 hasConcept C151730666 @default.
• W1882350379 hasConcept C154945302 @default.
• W1882350379 hasConcept C185592680 @default.
• W1882350379 hasConcept C2778403875 @default.
• W1882350379 hasConcept C2779343474 @default.
• W1882350379 hasConcept C37736160 @default.
• W1882350379 hasConcept C38652104 @default.
• W1882350379 hasConcept C41008148 @default.
• W1882350379 hasConcept C51632099 @default.
• W1882350379 hasConcept C55493867 @default.
• W1882350379 hasConcept C62230096 @default.
• W1882350379 hasConcept C63479239 @default.
• W1882350379 hasConcept C86803240 @default.
• W1882350379 hasConceptScore W1882350379C104317684 @default.
• W1882350379 hasConceptScore W1882350379C119857082 @default.
• W1882350379 hasConceptScore W1882350379C136764020 @default.
• W1882350379 hasConceptScore W1882350379C146849305 @default.
• W1882350379 hasConceptScore W1882350379C151730666 @default.
• W1882350379 hasConceptScore W1882350379C154945302 @default.
• W1882350379 hasConceptScore W1882350379C185592680 @default.

• next