Matches in SemOpenAlex for { <https://semopenalex.org/work/W3204815074> ?p ?o ?g. }
- W3204815074 abstract "In this paper, we investigate how to manipulate the coefficients obtained via linear regression by adding carefully designed poisoning data points to the dataset or modify the original data points. Given the energy budget, we first provide the closed-form solution of the optimal poisoning data point when our target is modifying one designated regression coefficient. We then extend the analysis to the more challenging scenario where the attacker aims to change one particular regression coefficient while making others to be changed as small as possible. For this scenario, we introduce a semidefinite relaxation method to design the best attack scheme. Finally, we study a more powerful adversary who can perform a rank-one modification on the feature matrix. We propose an alternating optimization method to find the optimal rank-one modification matrix. Numerical examples are provided to illustrate the analytical results obtained in this paper." @default.
- W3204815074 created "2021-10-11" @default.
- W3204815074 creator A5009164482 @default.
- W3204815074 creator A5047667763 @default.
- W3204815074 creator A5081715462 @default.
- W3204815074 date "2021-01-01" @default.
- W3204815074 modified "2023-10-03" @default.
- W3204815074 title "Optimal Feature Manipulation Attacks Against Linear Regression" @default.
- W3204815074 cites W1590002045 @default.
- W3204815074 cites W1683291642 @default.
- W3204815074 cites W1967344706 @default.
- W3204815074 cites W1980486587 @default.
- W3204815074 cites W2057317983 @default.
- W3204815074 cites W2082639035 @default.
- W3204815074 cites W2109862542 @default.
- W3204815074 cites W2112507308 @default.
- W3204815074 cites W2135046866 @default.
- W3204815074 cites W2135912864 @default.
- W3204815074 cites W2155804346 @default.
- W3204815074 cites W2163924219 @default.
- W3204815074 cites W2165281529 @default.
- W3204815074 cites W2165933227 @default.
- W3204815074 cites W2170918767 @default.
- W3204815074 cites W2187013920 @default.
- W3204815074 cites W2214362489 @default.
- W3204815074 cites W2293844262 @default.
- W3204815074 cites W2296319761 @default.
- W3204815074 cites W2536620281 @default.
- W3204815074 cites W2557044351 @default.
- W3204815074 cites W2593062745 @default.
- W3204815074 cites W2595142274 @default.
- W3204815074 cites W2603766943 @default.
- W3204815074 cites W2604524164 @default.
- W3204815074 cites W2618043096 @default.
- W3204815074 cites W2742231817 @default.
- W3204815074 cites W2774423163 @default.
- W3204815074 cites W2809895662 @default.
- W3204815074 cites W2909023102 @default.
- W3204815074 cites W2913535645 @default.
- W3204815074 cites W2924551358 @default.
- W3204815074 cites W2954420970 @default.
- W3204815074 cites W2962763344 @default.
- W3204815074 cites W2963207607 @default.
- W3204815074 cites W2963343288 @default.
- W3204815074 cites W2964043980 @default.
- W3204815074 cites W2968611582 @default.
- W3204815074 cites W2968867107 @default.
- W3204815074 cites W3100944043 @default.
- W3204815074 cites W3104141960 @default.
- W3204815074 cites W3105479728 @default.
- W3204815074 cites W3120740533 @default.
- W3204815074 cites W652265168 @default.
- W3204815074 doi "https://doi.org/10.1109/tsp.2021.3115951" @default.
- W3204815074 hasPublicationYear "2021" @default.
- W3204815074 type Work @default.
- W3204815074 sameAs 3204815074 @default.
- W3204815074 citedByCount "1" @default.
- W3204815074 countsByYear W32048150742022 @default.
- W3204815074 crossrefType "journal-article" @default.
- W3204815074 hasAuthorship W3204815074A5009164482 @default.
- W3204815074 hasAuthorship W3204815074A5047667763 @default.
- W3204815074 hasAuthorship W3204815074A5081715462 @default.
- W3204815074 hasBestOaLocation W32048150741 @default.
- W3204815074 hasConcept C105795698 @default.
- W3204815074 hasConcept C106487976 @default.
- W3204815074 hasConcept C11413529 @default.
- W3204815074 hasConcept C114614502 @default.
- W3204815074 hasConcept C119857082 @default.
- W3204815074 hasConcept C121332964 @default.
- W3204815074 hasConcept C126255220 @default.
- W3204815074 hasConcept C138885662 @default.
- W3204815074 hasConcept C148483581 @default.
- W3204815074 hasConcept C154945302 @default.
- W3204815074 hasConcept C15744967 @default.
- W3204815074 hasConcept C158693339 @default.
- W3204815074 hasConcept C159985019 @default.
- W3204815074 hasConcept C164226766 @default.
- W3204815074 hasConcept C192562407 @default.
- W3204815074 hasConcept C203233044 @default.
- W3204815074 hasConcept C2776029896 @default.
- W3204815074 hasConcept C2776401178 @default.
- W3204815074 hasConcept C33923547 @default.
- W3204815074 hasConcept C41008148 @default.
- W3204815074 hasConcept C41895202 @default.
- W3204815074 hasConcept C48921125 @default.
- W3204815074 hasConcept C60866291 @default.
- W3204815074 hasConcept C62520636 @default.
- W3204815074 hasConcept C77805123 @default.
- W3204815074 hasConcept C83546350 @default.
- W3204815074 hasConceptScore W3204815074C105795698 @default.
- W3204815074 hasConceptScore W3204815074C106487976 @default.
- W3204815074 hasConceptScore W3204815074C11413529 @default.
- W3204815074 hasConceptScore W3204815074C114614502 @default.
- W3204815074 hasConceptScore W3204815074C119857082 @default.
- W3204815074 hasConceptScore W3204815074C121332964 @default.
- W3204815074 hasConceptScore W3204815074C126255220 @default.
- W3204815074 hasConceptScore W3204815074C138885662 @default.
- W3204815074 hasConceptScore W3204815074C148483581 @default.
- W3204815074 hasConceptScore W3204815074C154945302 @default.
- W3204815074 hasConceptScore W3204815074C15744967 @default.