FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891828758> ?p ?o ?g. }

• W2891828758 endingPage "16" @default.
• W2891828758 startingPage "1" @default.
• W2891828758 abstract "Deep neural networks (DNNs) have shown huge superiority over humans in image recognition, speech processing, autonomous vehicles, and medical diagnosis. However, recent studies indicate that DNNs are vulnerable to adversarial examples (AEs), which are designed by attackers to fool deep learning models. Different from real examples, AEs can mislead the model to predict incorrect outputs while hardly be distinguished by human eyes, therefore threaten security-critical deep-learning applications. In recent years, the generation and defense of AEs have become a research hotspot in the field of artificial intelligence (AI) security. This article reviews the latest research progress of AEs. First, we introduce the concept, cause, characteristics, and evaluation metrics of AEs, then give a survey on the state-of-the-art AE generation methods with the discussion of advantages and disadvantages. After that, we review the existing defenses and discuss their limitations. Finally, future research opportunities and challenges on AEs are prospected." @default.
• W2891828758 created "2018-09-27" @default.
• W2891828758 creator A5007715345 @default.
• W2891828758 creator A5032447166 @default.
• W2891828758 date "2019-01-01" @default.
• W2891828758 modified "2023-10-16" @default.
• W2891828758 title "Adversarial Examples: Opportunities and Challenges" @default.
• W2891828758 cites W1590456070 @default.
• W2891828758 cites W2007562169 @default.
• W2891828758 cites W2032972350 @default.
• W2891828758 cites W2067008732 @default.
• W2891828758 cites W2088454850 @default.
• W2891828758 cites W2095195675 @default.
• W2891828758 cites W2117539524 @default.
• W2891828758 cites W2133665775 @default.
• W2891828758 cites W2151298633 @default.
• W2891828758 cites W2180612164 @default.
• W2891828758 cites W2183341477 @default.
• W2891828758 cites W2194775991 @default.
• W2891828758 cites W2243397390 @default.
• W2891828758 cites W2293768274 @default.
• W2891828758 cites W2296452361 @default.
• W2891828758 cites W2479004360 @default.
• W2891828758 cites W2533641151 @default.
• W2891828758 cites W2543927648 @default.
• W2891828758 cites W2559010931 @default.
• W2891828758 cites W2561975083 @default.
• W2891828758 cites W2603766943 @default.
• W2891828758 cites W2604505099 @default.
• W2891828758 cites W2611576673 @default.
• W2891828758 cites W2618043096 @default.
• W2891828758 cites W2744095836 @default.
• W2891828758 cites W2745565856 @default.
• W2891828758 cites W2774253509 @default.
• W2891828758 cites W2774644650 @default.
• W2891828758 cites W2791319131 @default.
• W2891828758 cites W2811491745 @default.
• W2891828758 cites W2887603965 @default.
• W2891828758 cites W2897573479 @default.
• W2891828758 cites W2949639282 @default.
• W2891828758 cites W2962995403 @default.
• W2891828758 cites W2963098487 @default.
• W2891828758 cites W2963178695 @default.
• W2891828758 cites W2963446712 @default.
• W2891828758 cites W2963564844 @default.
• W2891828758 cites W2963739340 @default.
• W2891828758 cites W2963857521 @default.
• W2891828758 cites W2964082701 @default.
• W2891828758 cites W2971718024 @default.
• W2891828758 cites W2975763460 @default.
• W2891828758 cites W3103277946 @default.
• W2891828758 cites W3103557498 @default.
• W2891828758 cites W4247200422 @default.
• W2891828758 doi "https://doi.org/10.1109/tnnls.2019.2933524" @default.
• W2891828758 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31722487" @default.
• W2891828758 hasPublicationYear "2019" @default.
• W2891828758 type Work @default.
• W2891828758 sameAs 2891828758 @default.
• W2891828758 citedByCount "63" @default.
• W2891828758 countsByYear W28918287582017 @default.
• W2891828758 countsByYear W28918287582018 @default.
• W2891828758 countsByYear W28918287582019 @default.
• W2891828758 countsByYear W28918287582020 @default.
• W2891828758 countsByYear W28918287582021 @default.
• W2891828758 countsByYear W28918287582022 @default.
• W2891828758 countsByYear W28918287582023 @default.
• W2891828758 crossrefType "journal-article" @default.
• W2891828758 hasAuthorship W2891828758A5007715345 @default.
• W2891828758 hasAuthorship W2891828758A5032447166 @default.
• W2891828758 hasBestOaLocation W28918287582 @default.
• W2891828758 hasConcept C108583219 @default.
• W2891828758 hasConcept C119857082 @default.
• W2891828758 hasConcept C127313418 @default.
• W2891828758 hasConcept C146481406 @default.
• W2891828758 hasConcept C154945302 @default.
• W2891828758 hasConcept C202444582 @default.
• W2891828758 hasConcept C2522767166 @default.
• W2891828758 hasConcept C2984842247 @default.
• W2891828758 hasConcept C33923547 @default.
• W2891828758 hasConcept C37736160 @default.
• W2891828758 hasConcept C38652104 @default.
• W2891828758 hasConcept C41008148 @default.
• W2891828758 hasConcept C8058405 @default.
• W2891828758 hasConcept C9652623 @default.
• W2891828758 hasConceptScore W2891828758C108583219 @default.
• W2891828758 hasConceptScore W2891828758C119857082 @default.
• W2891828758 hasConceptScore W2891828758C127313418 @default.
• W2891828758 hasConceptScore W2891828758C146481406 @default.
• W2891828758 hasConceptScore W2891828758C154945302 @default.
• W2891828758 hasConceptScore W2891828758C202444582 @default.
• W2891828758 hasConceptScore W2891828758C2522767166 @default.
• W2891828758 hasConceptScore W2891828758C2984842247 @default.
• W2891828758 hasConceptScore W2891828758C33923547 @default.
• W2891828758 hasConceptScore W2891828758C37736160 @default.
• W2891828758 hasConceptScore W2891828758C38652104 @default.
• W2891828758 hasConceptScore W2891828758C41008148 @default.
• W2891828758 hasConceptScore W2891828758C8058405 @default.
• W2891828758 hasConceptScore W2891828758C9652623 @default.

• next