Matches in SemOpenAlex for { <https://semopenalex.org/work/W3001011010> ?p ?o ?g. }
- W3001011010 abstract "As the prevalence of deep learning in computer vision, adversarial samples that weaken the neural networks emerge in large numbers, revealing their deep-rooted defects. Most adversarial attacks calculate an imperceptible perturbation in image space to fool the DNNs. In this strategy, the perturbation looks like noise and thus could be mitigated. Attacks in feature space produce semantic perturbation, but they could only deal with low resolution samples. The reason lies in the great number of coupled features to express a high-resolution image. In this paper, we propose Attack by Identifying Effective Features (AIEF), which learns different weights for features to attack. Effective features, those with great weights, influence the victim model much but distort the image little, and thus are more effective for attack. By attacking mostly on them, AIEF produces high resolution adversarial samples with acceptable distortions. We demonstrate the effectiveness of AIEF by attacking on different tasks with different generative models." @default.
- W3001011010 created "2020-01-30" @default.
- W3001011010 creator A5026169938 @default.
- W3001011010 creator A5033196884 @default.
- W3001011010 creator A5066658925 @default.
- W3001011010 creator A5071654034 @default.
- W3001011010 creator A5085545406 @default.
- W3001011010 date "2020-01-21" @default.
- W3001011010 modified "2023-09-24" @default.
- W3001011010 title "Generate High-Resolution Adversarial Samples by Identifying Effective Features" @default.
- W3001011010 cites W1686810756 @default.
- W3001011010 cites W1731081199 @default.
- W3001011010 cites W2108598243 @default.
- W3001011010 cites W2194775991 @default.
- W3001011010 cites W2893749619 @default.
- W3001011010 cites W2919115771 @default.
- W3001011010 cites W2945359720 @default.
- W3001011010 cites W2962770929 @default.
- W3001011010 cites W2963384482 @default.
- W3001011010 cites W2963446712 @default.
- W3001011010 cites W2963709863 @default.
- W3001011010 cites W2963857521 @default.
- W3001011010 cites W2963920068 @default.
- W3001011010 cites W2964121744 @default.
- W3001011010 cites W2964153729 @default.
- W3001011010 cites W2964238361 @default.
- W3001011010 cites W2969542116 @default.
- W3001011010 cites W2970115835 @default.
- W3001011010 cites W2970971581 @default.
- W3001011010 cites W2971109239 @default.
- W3001011010 hasPublicationYear "2020" @default.
- W3001011010 type Work @default.
- W3001011010 sameAs 3001011010 @default.
- W3001011010 citedByCount "0" @default.
- W3001011010 crossrefType "posted-content" @default.
- W3001011010 hasAuthorship W3001011010A5026169938 @default.
- W3001011010 hasAuthorship W3001011010A5033196884 @default.
- W3001011010 hasAuthorship W3001011010A5066658925 @default.
- W3001011010 hasAuthorship W3001011010A5071654034 @default.
- W3001011010 hasAuthorship W3001011010A5085545406 @default.
- W3001011010 hasConcept C115961682 @default.
- W3001011010 hasConcept C119857082 @default.
- W3001011010 hasConcept C121332964 @default.
- W3001011010 hasConcept C153180895 @default.
- W3001011010 hasConcept C154945302 @default.
- W3001011010 hasConcept C177918212 @default.
- W3001011010 hasConcept C205649164 @default.
- W3001011010 hasConcept C2984842247 @default.
- W3001011010 hasConcept C2988773926 @default.
- W3001011010 hasConcept C3019883945 @default.
- W3001011010 hasConcept C3020199158 @default.
- W3001011010 hasConcept C37736160 @default.
- W3001011010 hasConcept C39890363 @default.
- W3001011010 hasConcept C41008148 @default.
- W3001011010 hasConcept C50644808 @default.
- W3001011010 hasConcept C62520636 @default.
- W3001011010 hasConcept C62649853 @default.
- W3001011010 hasConceptScore W3001011010C115961682 @default.
- W3001011010 hasConceptScore W3001011010C119857082 @default.
- W3001011010 hasConceptScore W3001011010C121332964 @default.
- W3001011010 hasConceptScore W3001011010C153180895 @default.
- W3001011010 hasConceptScore W3001011010C154945302 @default.
- W3001011010 hasConceptScore W3001011010C177918212 @default.
- W3001011010 hasConceptScore W3001011010C205649164 @default.
- W3001011010 hasConceptScore W3001011010C2984842247 @default.
- W3001011010 hasConceptScore W3001011010C2988773926 @default.
- W3001011010 hasConceptScore W3001011010C3019883945 @default.
- W3001011010 hasConceptScore W3001011010C3020199158 @default.
- W3001011010 hasConceptScore W3001011010C37736160 @default.
- W3001011010 hasConceptScore W3001011010C39890363 @default.
- W3001011010 hasConceptScore W3001011010C41008148 @default.
- W3001011010 hasConceptScore W3001011010C50644808 @default.
- W3001011010 hasConceptScore W3001011010C62520636 @default.
- W3001011010 hasConceptScore W3001011010C62649853 @default.
- W3001011010 hasLocation W30010110101 @default.
- W3001011010 hasOpenAccess W3001011010 @default.
- W3001011010 hasPrimaryLocation W30010110101 @default.
- W3001011010 hasRelatedWork W2606529538 @default.
- W3001011010 hasRelatedWork W2762664271 @default.
- W3001011010 hasRelatedWork W2895955590 @default.
- W3001011010 hasRelatedWork W2902127718 @default.
- W3001011010 hasRelatedWork W2918863780 @default.
- W3001011010 hasRelatedWork W2933354923 @default.
- W3001011010 hasRelatedWork W2953790959 @default.
- W3001011010 hasRelatedWork W2954523279 @default.
- W3001011010 hasRelatedWork W2963491874 @default.
- W3001011010 hasRelatedWork W2965806993 @default.
- W3001011010 hasRelatedWork W2997501521 @default.
- W3001011010 hasRelatedWork W2999612054 @default.
- W3001011010 hasRelatedWork W3021931631 @default.
- W3001011010 hasRelatedWork W3043635682 @default.
- W3001011010 hasRelatedWork W3109756630 @default.
- W3001011010 hasRelatedWork W3122196421 @default.
- W3001011010 hasRelatedWork W3154755065 @default.
- W3001011010 hasRelatedWork W3171219085 @default.
- W3001011010 hasRelatedWork W3176913710 @default.
- W3001011010 hasRelatedWork W3193733033 @default.
- W3001011010 isParatext "false" @default.
- W3001011010 isRetracted "false" @default.
- W3001011010 magId "3001011010" @default.