Matches in SemOpenAlex for { <https://semopenalex.org/work/W4318604526> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4318604526 abstract "Neural networks are vulnerable to adversarial attacks formed by minuscule perturbations to the original data. These perturbations lead to significant performance degradation. Previous works on defenses against adversarial evasion attacks typically involve pre-processing input data at training or testing time, or modifications to the objective function optimized during the training. In contrast, relatively fewer defense methods focus on modifying the topology and functionality of the underlying defended neural network. Additionally, prior theoretical examinations of the geometry of adversarial examples reveal a challenging and intrinsic trade-off between adversarial and benign accuracy. We introduce a novel modification to a traditional feed-forward convolutional neural network that embeds uncertainty within the network's hidden representations in a learned and data-dependent manner. Our proposed alteration renders the network significantly more resilient than comparably computationally expensive alternatives. Further, the empirical investigation of the proposed defense demonstrates that, unlike prior defense techniques that are comparable to state-of-the-art, the stochastic resonance effect improves adversarial accuracy without significant degradation in benign accuracy." @default.
- W4318604526 created "2023-01-31" @default.
- W4318604526 creator A5023565753 @default.
- W4318604526 creator A5079638101 @default.
- W4318604526 date "2022-12-04" @default.
- W4318604526 modified "2023-10-18" @default.
- W4318604526 title "On Reducing Adversarial Vulnerability with Data Dependent Stochastic Resonance" @default.
- W4318604526 cites W1928278792 @default.
- W4318604526 cites W2064675550 @default.
- W4318604526 cites W2111162236 @default.
- W4318604526 cites W2112796928 @default.
- W4318604526 cites W2127628742 @default.
- W4318604526 cites W2194775991 @default.
- W4318604526 cites W2211722331 @default.
- W4318604526 cites W2342045095 @default.
- W4318604526 cites W2371684294 @default.
- W4318604526 cites W2766447205 @default.
- W4318604526 cites W2774018344 @default.
- W4318604526 cites W2786055572 @default.
- W4318604526 cites W2794002979 @default.
- W4318604526 cites W2895948774 @default.
- W4318604526 cites W2963626858 @default.
- W4318604526 cites W2963857521 @default.
- W4318604526 cites W2964186415 @default.
- W4318604526 cites W2964350391 @default.
- W4318604526 cites W3005576178 @default.
- W4318604526 cites W3024197903 @default.
- W4318604526 cites W3031351653 @default.
- W4318604526 cites W3036048022 @default.
- W4318604526 cites W3199229028 @default.
- W4318604526 cites W4205633207 @default.
- W4318604526 cites W4207022562 @default.
- W4318604526 cites W4210656949 @default.
- W4318604526 cites W4247200422 @default.
- W4318604526 doi "https://doi.org/10.1109/ssci51031.2022.10022248" @default.
- W4318604526 hasPublicationYear "2022" @default.
- W4318604526 type Work @default.
- W4318604526 citedByCount "0" @default.
- W4318604526 crossrefType "proceedings-article" @default.
- W4318604526 hasAuthorship W4318604526A5023565753 @default.
- W4318604526 hasAuthorship W4318604526A5079638101 @default.
- W4318604526 hasConcept C111919701 @default.
- W4318604526 hasConcept C119857082 @default.
- W4318604526 hasConcept C120665830 @default.
- W4318604526 hasConcept C121332964 @default.
- W4318604526 hasConcept C14036430 @default.
- W4318604526 hasConcept C154945302 @default.
- W4318604526 hasConcept C192209626 @default.
- W4318604526 hasConcept C199845137 @default.
- W4318604526 hasConcept C2984842247 @default.
- W4318604526 hasConcept C37736160 @default.
- W4318604526 hasConcept C38652104 @default.
- W4318604526 hasConcept C41008148 @default.
- W4318604526 hasConcept C50644808 @default.
- W4318604526 hasConcept C78458016 @default.
- W4318604526 hasConcept C81363708 @default.
- W4318604526 hasConcept C86803240 @default.
- W4318604526 hasConcept C95713431 @default.
- W4318604526 hasConceptScore W4318604526C111919701 @default.
- W4318604526 hasConceptScore W4318604526C119857082 @default.
- W4318604526 hasConceptScore W4318604526C120665830 @default.
- W4318604526 hasConceptScore W4318604526C121332964 @default.
- W4318604526 hasConceptScore W4318604526C14036430 @default.
- W4318604526 hasConceptScore W4318604526C154945302 @default.
- W4318604526 hasConceptScore W4318604526C192209626 @default.
- W4318604526 hasConceptScore W4318604526C199845137 @default.
- W4318604526 hasConceptScore W4318604526C2984842247 @default.
- W4318604526 hasConceptScore W4318604526C37736160 @default.
- W4318604526 hasConceptScore W4318604526C38652104 @default.
- W4318604526 hasConceptScore W4318604526C41008148 @default.
- W4318604526 hasConceptScore W4318604526C50644808 @default.
- W4318604526 hasConceptScore W4318604526C78458016 @default.
- W4318604526 hasConceptScore W4318604526C81363708 @default.
- W4318604526 hasConceptScore W4318604526C86803240 @default.
- W4318604526 hasConceptScore W4318604526C95713431 @default.
- W4318604526 hasLocation W43186045261 @default.
- W4318604526 hasOpenAccess W4318604526 @default.
- W4318604526 hasPrimaryLocation W43186045261 @default.
- W4318604526 hasRelatedWork W2946727698 @default.
- W4318604526 hasRelatedWork W3027997911 @default.
- W4318604526 hasRelatedWork W3034953030 @default.
- W4318604526 hasRelatedWork W3194550388 @default.
- W4318604526 hasRelatedWork W4287025788 @default.
- W4318604526 hasRelatedWork W4287776258 @default.
- W4318604526 hasRelatedWork W4292794309 @default.
- W4318604526 hasRelatedWork W4293054861 @default.
- W4318604526 hasRelatedWork W4327499916 @default.
- W4318604526 hasRelatedWork W1629725936 @default.
- W4318604526 isParatext "false" @default.
- W4318604526 isRetracted "false" @default.
- W4318604526 workType "article" @default.