FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3025279871> ?p ?o ?g. }

• W3025279871 abstract "Nowadays, autonomous driving has attracted much attention from both industry and academia. Convolutional neural network (CNN) is a key component in autonomous driving, which is also increasingly adopted in pervasive computing such as smartphones, wearable devices, and IoT networks. Prior work shows CNN-based classification models are vulnerable to adversarial attacks. However, it is uncertain to what extent regression models such as driving models are vulnerable to adversarial attacks, the effectiveness of existing defense techniques, and the defense implications for system and middleware builders. This paper presents an in-depth analysis of five adversarial attacks and four defense methods on three driving models. Experiments show that, similar to classification models, these models are still highly vulnerable to adversarial attacks. This poses a big security threat to autonomous driving and thus should be taken into account in practice. While these defense methods can effectively defend against different attacks, none of them are able to provide adequate protection against all five attacks. We derive several implications for system and middleware builders: (1) when adding a defense component against adversarial attacks, it is important to deploy multiple defense methods in tandem to achieve a good coverage of various attacks, (2) a blackbox attack is much less effective compared with a white-box attack, implying that it is important to keep model details (e.g., model architecture, hyperparameters) confidential via model obfuscation, and (3) driving models with a complex architecture are preferred if computing resources permit as they are more resilient to adversarial attacks than simple models." @default.
• W3025279871 created "2020-05-21" @default.
• W3025279871 creator A5019279449 @default.
• W3025279871 creator A5049451101 @default.
• W3025279871 creator A5063253432 @default.
• W3025279871 creator A5068349578 @default.
• W3025279871 creator A5073806117 @default.
• W3025279871 creator A5081182489 @default.
• W3025279871 date "2020-03-01" @default.
• W3025279871 modified "2023-10-02" @default.
• W3025279871 title "An Analysis of Adversarial Attacks and Defenses on Autonomous Driving Models" @default.
• W3025279871 cites W1686810756 @default.
• W3025279871 cites W1793197839 @default.
• W3025279871 cites W2099471712 @default.
• W3025279871 cites W2100495367 @default.
• W3025279871 cites W2243397390 @default.
• W3025279871 cites W2342840547 @default.
• W3025279871 cites W2408141691 @default.
• W3025279871 cites W2537005174 @default.
• W3025279871 cites W2543296129 @default.
• W3025279871 cites W2543927648 @default.
• W3025279871 cites W2570685808 @default.
• W3025279871 cites W2603766943 @default.
• W3025279871 cites W2607219512 @default.
• W3025279871 cites W2617585083 @default.
• W3025279871 cites W2735607295 @default.
• W3025279871 cites W2767028498 @default.
• W3025279871 cites W2786070938 @default.
• W3025279871 cites W2808791761 @default.
• W3025279871 cites W2867167548 @default.
• W3025279871 cites W2888307014 @default.
• W3025279871 cites W2890038638 @default.
• W3025279871 cites W2962814013 @default.
• W3025279871 cites W2963001136 @default.
• W3025279871 cites W2963100962 @default.
• W3025279871 cites W2963178695 @default.
• W3025279871 cites W2963207607 @default.
• W3025279871 cites W2963327228 @default.
• W3025279871 cites W2963389226 @default.
• W3025279871 cites W2963431851 @default.
• W3025279871 cites W2963448658 @default.
• W3025279871 cites W2963496101 @default.
• W3025279871 cites W2963542245 @default.
• W3025279871 cites W2963566318 @default.
• W3025279871 cites W2963855547 @default.
• W3025279871 cites W2963857521 @default.
• W3025279871 cites W2963942203 @default.
• W3025279871 cites W2964082701 @default.
• W3025279871 cites W2964121744 @default.
• W3025279871 cites W2964153729 @default.
• W3025279871 cites W2964318098 @default.
• W3025279871 cites W2969695741 @default.
• W3025279871 doi "https://doi.org/10.1109/percom45495.2020.9127389" @default.
• W3025279871 hasPublicationYear "2020" @default.
• W3025279871 type Work @default.
• W3025279871 sameAs 3025279871 @default.
• W3025279871 citedByCount "67" @default.
• W3025279871 countsByYear W30252798712020 @default.
• W3025279871 countsByYear W30252798712021 @default.
• W3025279871 countsByYear W30252798712022 @default.
• W3025279871 countsByYear W30252798712023 @default.
• W3025279871 crossrefType "proceedings-article" @default.
• W3025279871 hasAuthorship W3025279871A5019279449 @default.
• W3025279871 hasAuthorship W3025279871A5049451101 @default.
• W3025279871 hasAuthorship W3025279871A5063253432 @default.
• W3025279871 hasAuthorship W3025279871A5068349578 @default.
• W3025279871 hasAuthorship W3025279871A5073806117 @default.
• W3025279871 hasAuthorship W3025279871A5081182489 @default.
• W3025279871 hasBestOaLocation W30252798712 @default.
• W3025279871 hasConcept C120314980 @default.
• W3025279871 hasConcept C121332964 @default.
• W3025279871 hasConcept C140547941 @default.
• W3025279871 hasConcept C154945302 @default.
• W3025279871 hasConcept C168167062 @default.
• W3025279871 hasConcept C169468491 @default.
• W3025279871 hasConcept C26517878 @default.
• W3025279871 hasConcept C37736160 @default.
• W3025279871 hasConcept C38652104 @default.
• W3025279871 hasConcept C40305131 @default.
• W3025279871 hasConcept C41008148 @default.
• W3025279871 hasConcept C97355855 @default.
• W3025279871 hasConceptScore W3025279871C120314980 @default.
• W3025279871 hasConceptScore W3025279871C121332964 @default.
• W3025279871 hasConceptScore W3025279871C140547941 @default.
• W3025279871 hasConceptScore W3025279871C154945302 @default.
• W3025279871 hasConceptScore W3025279871C168167062 @default.
• W3025279871 hasConceptScore W3025279871C169468491 @default.
• W3025279871 hasConceptScore W3025279871C26517878 @default.
• W3025279871 hasConceptScore W3025279871C37736160 @default.
• W3025279871 hasConceptScore W3025279871C38652104 @default.
• W3025279871 hasConceptScore W3025279871C40305131 @default.
• W3025279871 hasConceptScore W3025279871C41008148 @default.
• W3025279871 hasConceptScore W3025279871C97355855 @default.
• W3025279871 hasLocation W30252798711 @default.
• W3025279871 hasLocation W30252798712 @default.
• W3025279871 hasOpenAccess W3025279871 @default.
• W3025279871 hasPrimaryLocation W30252798711 @default.
• W3025279871 hasRelatedWork W107995937 @default.
• W3025279871 hasRelatedWork W1502821974 @default.
• W3025279871 hasRelatedWork W1553803634 @default.

• next