Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100694715> ?p ?o ?g. }
- W3100694715 endingPage "164" @default.
- W3100694715 startingPage "155" @default.
- W3100694715 abstract "Data-driven techniques are used in cyber-physical systems (CPS) for controlling autonomous vehicles, handling demand responses for energy management, and modeling human physiology for medical devices. These data-driven techniques extract models from training data, where their performance is often analyzed with respect to random errors in the training data. However, if the training data is maliciously altered by attackers, the effect of these attacks on the learning algorithms underpinning data-driven CPS have yet to be considered. In this paper, we analyze the resilience of classification algorithms to training data attacks. Specifically, a generic metric is proposed that is tailored to measure resilience of classification algorithms with respect to worst-case tampering of the training data. Using the metric, we show that traditional linear classification algorithms are resilient under restricted conditions. To overcome these limitations, we propose a linear classification algorithm with a majority constraint and prove that it is strictly more resilient than the traditional algorithms. Evaluations on both synthetic data and a real-world retrospective arrhythmia medical case-study show that the traditional algorithms are vulnerable to tampered training data, whereas the proposed algorithm is more resilient (as measured by worst-case tampering)." @default.
- W3100694715 created "2020-11-23" @default.
- W3100694715 creator A5014443062 @default.
- W3100694715 creator A5030456600 @default.
- W3100694715 creator A5054356243 @default.
- W3100694715 date "2017-04-18" @default.
- W3100694715 modified "2023-09-23" @default.
- W3100694715 title "Resilient linear classification: an approach to deal with attacks on training data" @default.
- W3100694715 cites W1470570003 @default.
- W3100694715 cites W1500551892 @default.
- W3100694715 cites W185142374 @default.
- W3100694715 cites W1877206914 @default.
- W3100694715 cites W1905905554 @default.
- W3100694715 cites W1945616565 @default.
- W3100694715 cites W1960174506 @default.
- W3100694715 cites W1963576557 @default.
- W3100694715 cites W1966912382 @default.
- W3100694715 cites W1968998685 @default.
- W3100694715 cites W1974122854 @default.
- W3100694715 cites W1982032418 @default.
- W3100694715 cites W1995810576 @default.
- W3100694715 cites W2003530067 @default.
- W3100694715 cites W2005302181 @default.
- W3100694715 cites W2021885139 @default.
- W3100694715 cites W2024139303 @default.
- W3100694715 cites W2062132646 @default.
- W3100694715 cites W2064684330 @default.
- W3100694715 cites W207267598 @default.
- W3100694715 cites W2089394015 @default.
- W3100694715 cites W2091825929 @default.
- W3100694715 cites W2103154003 @default.
- W3100694715 cites W2107189314 @default.
- W3100694715 cites W2107961375 @default.
- W3100694715 cites W2113290770 @default.
- W3100694715 cites W2115656617 @default.
- W3100694715 cites W2116520617 @default.
- W3100694715 cites W2119112357 @default.
- W3100694715 cites W2119821739 @default.
- W3100694715 cites W2134829400 @default.
- W3100694715 cites W2149298154 @default.
- W3100694715 cites W2149989524 @default.
- W3100694715 cites W2159294971 @default.
- W3100694715 cites W2163605009 @default.
- W3100694715 cites W2293768274 @default.
- W3100694715 cites W2293844262 @default.
- W3100694715 cites W2294903825 @default.
- W3100694715 cites W2408368322 @default.
- W3100694715 cites W2408503172 @default.
- W3100694715 cites W2566510693 @default.
- W3100694715 cites W2606754291 @default.
- W3100694715 cites W2949506549 @default.
- W3100694715 cites W2964153729 @default.
- W3100694715 cites W3120740533 @default.
- W3100694715 cites W54422097 @default.
- W3100694715 cites W815108739 @default.
- W3100694715 cites W9657784 @default.
- W3100694715 hasPublicationYear "2017" @default.
- W3100694715 type Work @default.
- W3100694715 sameAs 3100694715 @default.
- W3100694715 citedByCount "1" @default.
- W3100694715 countsByYear W31006947152019 @default.
- W3100694715 crossrefType "proceedings-article" @default.
- W3100694715 hasAuthorship W3100694715A5014443062 @default.
- W3100694715 hasAuthorship W3100694715A5030456600 @default.
- W3100694715 hasAuthorship W3100694715A5054356243 @default.
- W3100694715 hasBestOaLocation W31006947151 @default.
- W3100694715 hasConcept C119857082 @default.
- W3100694715 hasConcept C121332964 @default.
- W3100694715 hasConcept C124101348 @default.
- W3100694715 hasConcept C127413603 @default.
- W3100694715 hasConcept C153294291 @default.
- W3100694715 hasConcept C154945302 @default.
- W3100694715 hasConcept C176217482 @default.
- W3100694715 hasConcept C21547014 @default.
- W3100694715 hasConcept C2524010 @default.
- W3100694715 hasConcept C2776036281 @default.
- W3100694715 hasConcept C2777211547 @default.
- W3100694715 hasConcept C2779585090 @default.
- W3100694715 hasConcept C33923547 @default.
- W3100694715 hasConcept C41008148 @default.
- W3100694715 hasConcept C51632099 @default.
- W3100694715 hasConcept C67186912 @default.
- W3100694715 hasConcept C77088390 @default.
- W3100694715 hasConcept C97355855 @default.
- W3100694715 hasConceptScore W3100694715C119857082 @default.
- W3100694715 hasConceptScore W3100694715C121332964 @default.
- W3100694715 hasConceptScore W3100694715C124101348 @default.
- W3100694715 hasConceptScore W3100694715C127413603 @default.
- W3100694715 hasConceptScore W3100694715C153294291 @default.
- W3100694715 hasConceptScore W3100694715C154945302 @default.
- W3100694715 hasConceptScore W3100694715C176217482 @default.
- W3100694715 hasConceptScore W3100694715C21547014 @default.
- W3100694715 hasConceptScore W3100694715C2524010 @default.
- W3100694715 hasConceptScore W3100694715C2776036281 @default.
- W3100694715 hasConceptScore W3100694715C2777211547 @default.
- W3100694715 hasConceptScore W3100694715C2779585090 @default.
- W3100694715 hasConceptScore W3100694715C33923547 @default.
- W3100694715 hasConceptScore W3100694715C41008148 @default.