FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2799694080> ?p ?o ?g. }

• W2799694080 abstract "Users in various web and mobile applications are vulnerable to attribute inference attacks, in which an attacker leverages a machine learning classifier to infer a target user's private attributes (e.g., location, sexual orientation, political view) from its public data (e.g., rating scores, page likes). Existing defenses leverage game theory or heuristics based on correlations between the public data and attributes. These defenses are not practical. Specifically, game-theoretic defenses require solving intractable optimization problems, while correlation-based defenses incur large utility loss of users' public data. In this paper, we present AttriGuard, a practical defense against attribute inference attacks. AttriGuard is computationally tractable and has small utility loss. Our AttriGuard works in two phases. Suppose we aim to protect a user's private attribute. In Phase I, for each value of the attribute, we find a minimum noise such that if we add the noise to the user's public data, then the attacker's classifier is very likely to infer the attribute value for the user. We find the minimum noise via adapting existing evasion attacks in adversarial machine learning. In Phase II, we sample one attribute value according to a certain probability distribution and add the corresponding noise found in Phase I to the user's public data. We formulate finding the probability distribution as solving a constrained convex optimization problem. We extensively evaluate AttriGuard and compare it with existing methods using a real-world dataset. Our results show that AttriGuard substantially outperforms existing methods. Our work is the first one that shows evasion attacks can be used as defensive techniques for privacy protection." @default.
• W2799694080 created "2018-05-17" @default.
• W2799694080 creator A5009102659 @default.
• W2799694080 creator A5087464080 @default.
• W2799694080 date "2018-05-13" @default.
• W2799694080 modified "2023-09-27" @default.
• W2799694080 title "AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learning" @default.
• W2799694080 cites W114911201 @default.
• W2799694080 cites W1473189865 @default.
• W2799694080 cites W1665214252 @default.
• W2799694080 cites W1714669175 @default.
• W2799694080 cites W1873763122 @default.
• W2799694080 cites W1973556323 @default.
• W2799694080 cites W1992291252 @default.
• W2799694080 cites W2013823004 @default.
• W2799694080 cites W2028427195 @default.
• W2799694080 cites W2051267297 @default.
• W2799694080 cites W2053801139 @default.
• W2799694080 cites W2060871119 @default.
• W2799694080 cites W2103133870 @default.
• W2799694080 cites W2107933610 @default.
• W2799694080 cites W2109296207 @default.
• W2799694080 cites W2151298633 @default.
• W2799694080 cites W2153803020 @default.
• W2799694080 cites W2157568256 @default.
• W2799694080 cites W2159196732 @default.
• W2799694080 cites W2160642151 @default.
• W2799694080 cites W2180612164 @default.
• W2799694080 cites W2279779665 @default.
• W2799694080 cites W2509042760 @default.
• W2799694080 cites W2532967691 @default.
• W2799694080 cites W2535873859 @default.
• W2799694080 cites W2566989010 @default.
• W2799694080 cites W2570685808 @default.
• W2799694080 cites W2593892853 @default.
• W2799694080 cites W2603766943 @default.
• W2799694080 cites W2604776663 @default.
• W2799694080 cites W2652948231 @default.
• W2799694080 cites W2742225091 @default.
• W2799694080 cites W2781896769 @default.
• W2799694080 cites W2785557471 @default.
• W2799694080 cites W2950383328 @default.
• W2799694080 cites W2963158386 @default.
• W2799694080 cites W2963207607 @default.
• W2799694080 cites W2963389226 @default.
• W2799694080 cites W2963490108 @default.
• W2799694080 cites W2963535017 @default.
• W2799694080 cites W2963857521 @default.
• W2799694080 cites W2964019258 @default.
• W2799694080 cites W2964082701 @default.
• W2799694080 cites W3101704102 @default.
• W2799694080 cites W3102859907 @default.
• W2799694080 cites W9657784 @default.
• W2799694080 hasPublicationYear "2018" @default.
• W2799694080 type Work @default.
• W2799694080 sameAs 2799694080 @default.
• W2799694080 citedByCount "7" @default.
• W2799694080 countsByYear W27996940802017 @default.
• W2799694080 countsByYear W27996940802018 @default.
• W2799694080 countsByYear W27996940802019 @default.
• W2799694080 countsByYear W27996940802020 @default.
• W2799694080 countsByYear W27996940802021 @default.
• W2799694080 crossrefType "posted-content" @default.
• W2799694080 hasAuthorship W2799694080A5009102659 @default.
• W2799694080 hasAuthorship W2799694080A5087464080 @default.
• W2799694080 hasConcept C111919701 @default.
• W2799694080 hasConcept C119857082 @default.
• W2799694080 hasConcept C124101348 @default.
• W2799694080 hasConcept C127705205 @default.
• W2799694080 hasConcept C153083717 @default.
• W2799694080 hasConcept C154945302 @default.
• W2799694080 hasConcept C2776214188 @default.
• W2799694080 hasConcept C2778403875 @default.
• W2799694080 hasConcept C37736160 @default.
• W2799694080 hasConcept C41008148 @default.
• W2799694080 hasConcept C95623464 @default.
• W2799694080 hasConceptScore W2799694080C111919701 @default.
• W2799694080 hasConceptScore W2799694080C119857082 @default.
• W2799694080 hasConceptScore W2799694080C124101348 @default.
• W2799694080 hasConceptScore W2799694080C127705205 @default.
• W2799694080 hasConceptScore W2799694080C153083717 @default.
• W2799694080 hasConceptScore W2799694080C154945302 @default.
• W2799694080 hasConceptScore W2799694080C2776214188 @default.
• W2799694080 hasConceptScore W2799694080C2778403875 @default.
• W2799694080 hasConceptScore W2799694080C37736160 @default.
• W2799694080 hasConceptScore W2799694080C41008148 @default.
• W2799694080 hasConceptScore W2799694080C95623464 @default.
• W2799694080 hasLocation W27996940801 @default.
• W2799694080 hasOpenAccess W2799694080 @default.
• W2799694080 hasPrimaryLocation W27996940801 @default.
• W2799694080 hasRelatedWork W2040228409 @default.
• W2799694080 hasRelatedWork W2051267297 @default.
• W2799694080 hasRelatedWork W2099471712 @default.
• W2799694080 hasRelatedWork W2532520288 @default.
• W2799694080 hasRelatedWork W2535690855 @default.
• W2799694080 hasRelatedWork W2795435272 @default.
• W2799694080 hasRelatedWork W2884943453 @default.
• W2799694080 hasRelatedWork W2952270003 @default.
• W2799694080 hasRelatedWork W2963080984 @default.
• W2799694080 hasRelatedWork W2964151798 @default.

• next