FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3037965461> ?p ?o ?g. }

• W3037965461 abstract "State-of-the-art deep learning models are untrustworthy due to their vulnerability to adversarial examples. Intriguingly, besides simple adversarial perturbations, there exist Universal Adversarial Perturbations (UAPs), which are input-agnostic perturbations that lead to misclassification of majority inputs. The main target of existing adversarial examples (including UAPs) is to change primarily the correct Top-1 predicted class by the incorrect one, which does not guarantee changing the Top-k prediction. However, in many real-world scenarios, dealing with digital data, Top-k predictions are more important. We propose an effective geometry-inspired method of computing Top-k adversarial examples for any k. We evaluate its effectiveness and efficiency by comparing it with other adversarial example crafting techniques. Based on this method, we propose Top-k Universal Adversarial Perturbations, image-agnostic tiny perturbations that cause true class to be absent among the Top-k pre-diction. We experimentally show that our approach outperforms baseline methods and even improves existing techniques of generating UAPs." @default.
• W3037965461 created "2020-07-02" @default.
• W3037965461 creator A5004111307 @default.
• W3037965461 creator A5020804657 @default.
• W3037965461 creator A5030110484 @default.
• W3037965461 date "2020-06-28" @default.
• W3037965461 modified "2023-09-27" @default.
• W3037965461 title "Geometry-Inspired Top-k Adversarial Perturbations." @default.
• W3037965461 cites W1686810756 @default.
• W3037965461 cites W2112796928 @default.
• W3037965461 cites W2194775991 @default.
• W3037965461 cites W2243397390 @default.
• W3037965461 cites W2460937040 @default.
• W3037965461 cites W2535873859 @default.
• W3037965461 cites W2543927648 @default.
• W3037965461 cites W2609920186 @default.
• W3037965461 cites W2640329709 @default.
• W3037965461 cites W2738229973 @default.
• W3037965461 cites W2743499620 @default.
• W3037965461 cites W2748789698 @default.
• W3037965461 cites W2754808688 @default.
• W3037965461 cites W2782403400 @default.
• W3037965461 cites W2786807178 @default.
• W3037965461 cites W2787708942 @default.
• W3037965461 cites W2798302089 @default.
• W3037965461 cites W2890304135 @default.
• W3037965461 cites W2917779306 @default.
• W3037965461 cites W2943984343 @default.
• W3037965461 cites W2946213629 @default.
• W3037965461 cites W2963163009 @default.
• W3037965461 cites W2963165363 @default.
• W3037965461 cites W2963207607 @default.
• W3037965461 cites W2963516603 @default.
• W3037965461 cites W2963557656 @default.
• W3037965461 cites W2963809642 @default.
• W3037965461 cites W2963857521 @default.
• W3037965461 cites W2963899139 @default.
• W3037965461 cites W2964153729 @default.
• W3037965461 cites W2964171870 @default.
• W3037965461 cites W2964241437 @default.
• W3037965461 cites W2964301649 @default.
• W3037965461 cites W2966367171 @default.
• W3037965461 cites W2969664989 @default.
• W3037965461 cites W2983042735 @default.
• W3037965461 cites W2984884190 @default.
• W3037965461 cites W2996455429 @default.
• W3037965461 cites W3007305010 @default.
• W3037965461 cites W3035345420 @default.
• W3037965461 cites W3098018961 @default.
• W3037965461 cites W3106835084 @default.
• W3037965461 cites W3173901518 @default.
• W3037965461 hasPublicationYear "2020" @default.
• W3037965461 type Work @default.
• W3037965461 sameAs 3037965461 @default.
• W3037965461 citedByCount "2" @default.
• W3037965461 countsByYear W30379654612020 @default.
• W3037965461 countsByYear W30379654612021 @default.
• W3037965461 crossrefType "posted-content" @default.
• W3037965461 hasAuthorship W3037965461A5004111307 @default.
• W3037965461 hasAuthorship W3037965461A5020804657 @default.
• W3037965461 hasAuthorship W3037965461A5030110484 @default.
• W3037965461 hasConcept C11413529 @default.
• W3037965461 hasConcept C119857082 @default.
• W3037965461 hasConcept C154945302 @default.
• W3037965461 hasConcept C2777212361 @default.
• W3037965461 hasConcept C37736160 @default.
• W3037965461 hasConcept C41008148 @default.
• W3037965461 hasConcept C80444323 @default.
• W3037965461 hasConceptScore W3037965461C11413529 @default.
• W3037965461 hasConceptScore W3037965461C119857082 @default.
• W3037965461 hasConceptScore W3037965461C154945302 @default.
• W3037965461 hasConceptScore W3037965461C2777212361 @default.
• W3037965461 hasConceptScore W3037965461C37736160 @default.
• W3037965461 hasConceptScore W3037965461C41008148 @default.
• W3037965461 hasConceptScore W3037965461C80444323 @default.
• W3037965461 hasLocation W30379654611 @default.
• W3037965461 hasOpenAccess W3037965461 @default.
• W3037965461 hasPrimaryLocation W30379654611 @default.
• W3037965461 hasRelatedWork W2513314332 @default.
• W3037965461 hasRelatedWork W2612637113 @default.
• W3037965461 hasRelatedWork W2785466457 @default.
• W3037965461 hasRelatedWork W2787406324 @default.
• W3037965461 hasRelatedWork W2787480667 @default.
• W3037965461 hasRelatedWork W2889854042 @default.
• W3037965461 hasRelatedWork W2906761598 @default.
• W3037965461 hasRelatedWork W2963849784 @default.
• W3037965461 hasRelatedWork W2970504098 @default.
• W3037965461 hasRelatedWork W2990289029 @default.
• W3037965461 hasRelatedWork W3006044868 @default.
• W3037965461 hasRelatedWork W3022162782 @default.
• W3037965461 hasRelatedWork W3033740287 @default.
• W3037965461 hasRelatedWork W3039435622 @default.
• W3037965461 hasRelatedWork W3046426875 @default.
• W3037965461 hasRelatedWork W3100506997 @default.
• W3037965461 hasRelatedWork W3110934648 @default.
• W3037965461 hasRelatedWork W3130611678 @default.
• W3037965461 hasRelatedWork W3184325371 @default.
• W3037965461 hasRelatedWork W3203774412 @default.
• W3037965461 isParatext "false" @default.
• W3037965461 isRetracted "false" @default.

• next