Matches in SemOpenAlex for { <https://semopenalex.org/work/W3130050141> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W3130050141 abstract "Machine learning (ML) models are known to be vulnerable to attacks both at training and test time. Despite the extensive literature on adversarial ML, prior efforts focus primarily on applications of computer vision to object recognition or sentiment analysis to movie reviews. In these settings, the incentives for adversaries to manipulate the model's prediction are often unclear and attacks require extensive control of direct inputs to the model. This makes it difficult to evaluate how severe the impact of vulnerabilities exposed is on systems deploying ML with little provenance guarantees for the input data. In this paper, we study adversarial ML with stock price forecasting. Adversarial incentives are clear and may be quantified experimentally through a simulated portfolio. We replicate an industry standard pipeline, which performs a sentiment analysis of Twitter data to forecast trends in stock prices. We show that an adversary can exploit the lack of provenance to indirectly use tweets to manipulate the model's perceived sentiment about a target company and in turn force the model to forecast price erroneously. Our attack is mounted at test time and does not modify the training data. Given past market anomalies, we conclude with a series of recommendations for the use of machine learning as input signal to trading algorithms." @default.
- W3130050141 created "2021-03-01" @default.
- W3130050141 creator A5018809423 @default.
- W3130050141 creator A5082457354 @default.
- W3130050141 creator A5085218051 @default.
- W3130050141 date "2021-05-04" @default.
- W3130050141 modified "2023-09-27" @default.
- W3130050141 title "On the Robustness of Sentiment Analysis for Stock Price Forecasting" @default.
- W3130050141 hasPublicationYear "2021" @default.
- W3130050141 type Work @default.
- W3130050141 sameAs 3130050141 @default.
- W3130050141 citedByCount "0" @default.
- W3130050141 crossrefType "journal-article" @default.
- W3130050141 hasAuthorship W3130050141A5018809423 @default.
- W3130050141 hasAuthorship W3130050141A5082457354 @default.
- W3130050141 hasAuthorship W3130050141A5085218051 @default.
- W3130050141 hasConcept C10138342 @default.
- W3130050141 hasConcept C104317684 @default.
- W3130050141 hasConcept C105795698 @default.
- W3130050141 hasConcept C119857082 @default.
- W3130050141 hasConcept C127413603 @default.
- W3130050141 hasConcept C149782125 @default.
- W3130050141 hasConcept C154945302 @default.
- W3130050141 hasConcept C162324750 @default.
- W3130050141 hasConcept C165696696 @default.
- W3130050141 hasConcept C175444787 @default.
- W3130050141 hasConcept C185592680 @default.
- W3130050141 hasConcept C204036174 @default.
- W3130050141 hasConcept C2780821815 @default.
- W3130050141 hasConcept C2781162219 @default.
- W3130050141 hasConcept C29122968 @default.
- W3130050141 hasConcept C33923547 @default.
- W3130050141 hasConcept C37736160 @default.
- W3130050141 hasConcept C38652104 @default.
- W3130050141 hasConcept C41008148 @default.
- W3130050141 hasConcept C55493867 @default.
- W3130050141 hasConcept C63479239 @default.
- W3130050141 hasConcept C66402592 @default.
- W3130050141 hasConcept C78519656 @default.
- W3130050141 hasConceptScore W3130050141C10138342 @default.
- W3130050141 hasConceptScore W3130050141C104317684 @default.
- W3130050141 hasConceptScore W3130050141C105795698 @default.
- W3130050141 hasConceptScore W3130050141C119857082 @default.
- W3130050141 hasConceptScore W3130050141C127413603 @default.
- W3130050141 hasConceptScore W3130050141C149782125 @default.
- W3130050141 hasConceptScore W3130050141C154945302 @default.
- W3130050141 hasConceptScore W3130050141C162324750 @default.
- W3130050141 hasConceptScore W3130050141C165696696 @default.
- W3130050141 hasConceptScore W3130050141C175444787 @default.
- W3130050141 hasConceptScore W3130050141C185592680 @default.
- W3130050141 hasConceptScore W3130050141C204036174 @default.
- W3130050141 hasConceptScore W3130050141C2780821815 @default.
- W3130050141 hasConceptScore W3130050141C2781162219 @default.
- W3130050141 hasConceptScore W3130050141C29122968 @default.
- W3130050141 hasConceptScore W3130050141C33923547 @default.
- W3130050141 hasConceptScore W3130050141C37736160 @default.
- W3130050141 hasConceptScore W3130050141C38652104 @default.
- W3130050141 hasConceptScore W3130050141C41008148 @default.
- W3130050141 hasConceptScore W3130050141C55493867 @default.
- W3130050141 hasConceptScore W3130050141C63479239 @default.
- W3130050141 hasConceptScore W3130050141C66402592 @default.
- W3130050141 hasConceptScore W3130050141C78519656 @default.
- W3130050141 hasLocation W31300501411 @default.
- W3130050141 hasOpenAccess W3130050141 @default.
- W3130050141 hasPrimaryLocation W31300501411 @default.
- W3130050141 hasRelatedWork W1547039882 @default.
- W3130050141 hasRelatedWork W2029727871 @default.
- W3130050141 hasRelatedWork W2417939070 @default.
- W3130050141 hasRelatedWork W2893049941 @default.
- W3130050141 hasRelatedWork W2897494692 @default.
- W3130050141 hasRelatedWork W2919074916 @default.
- W3130050141 hasRelatedWork W2973765623 @default.
- W3130050141 hasRelatedWork W2979877996 @default.
- W3130050141 hasRelatedWork W3002348292 @default.
- W3130050141 hasRelatedWork W3092524902 @default.
- W3130050141 hasRelatedWork W3121647275 @default.
- W3130050141 hasRelatedWork W3126699780 @default.
- W3130050141 hasRelatedWork W3129691717 @default.
- W3130050141 hasRelatedWork W3130367027 @default.
- W3130050141 hasRelatedWork W3167321119 @default.
- W3130050141 hasRelatedWork W3167984817 @default.
- W3130050141 hasRelatedWork W3175215759 @default.
- W3130050141 hasRelatedWork W3175306752 @default.
- W3130050141 hasRelatedWork W3178576742 @default.
- W3130050141 hasRelatedWork W3208016573 @default.
- W3130050141 isParatext "false" @default.
- W3130050141 isRetracted "false" @default.
- W3130050141 magId "3130050141" @default.
- W3130050141 workType "article" @default.