Matches in SemOpenAlex for { <https://semopenalex.org/work/W3094319733> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3094319733 abstract "The robustness of deep neural networks against adversarial example attacks has received much attention recently. We focus on certified robustness of smoothed classifiers in this work, and propose to use the worst-case population loss over noisy inputs as a robustness metric. Under this metric, we provide a tractable upper bound serving as a robustness certificate by exploiting the duality. To improve the robustness, we further propose a noisy adversarial learning procedure to minimize the upper bound following the robust optimization framework. The smoothness of the loss function ensures the problem easy to optimize even for non-smooth neural networks. We show how our robustness certificate compares with others and the improvement over previous works. Experiments on a variety of datasets and models verify that in terms of empirical accuracies, our approach exceeds the state-of-the-art certified/heuristic methods in defending adversarial examples." @default.
- W3094319733 created "2020-10-29" @default.
- W3094319733 creator A5018175815 @default.
- W3094319733 creator A5034483183 @default.
- W3094319733 creator A5045198205 @default.
- W3094319733 creator A5046597133 @default.
- W3094319733 creator A5061642756 @default.
- W3094319733 creator A5072326707 @default.
- W3094319733 date "2020-10-21" @default.
- W3094319733 modified "2023-09-27" @default.
- W3094319733 title "A Distributional Robustness Certificate by Randomized Smoothing." @default.
- W3094319733 cites W2342045095 @default.
- W3094319733 cites W2767075075 @default.
- W3094319733 cites W2803850896 @default.
- W3094319733 cites W2807040120 @default.
- W3094319733 cites W2892354372 @default.
- W3094319733 cites W2913266441 @default.
- W3094319733 cites W2944407464 @default.
- W3094319733 cites W2962710014 @default.
- W3094319733 cites W2963207607 @default.
- W3094319733 cites W2963389226 @default.
- W3094319733 cites W2963496101 @default.
- W3094319733 cites W2970297683 @default.
- W3094319733 cites W2971109239 @default.
- W3094319733 hasPublicationYear "2020" @default.
- W3094319733 type Work @default.
- W3094319733 sameAs 3094319733 @default.
- W3094319733 citedByCount "0" @default.
- W3094319733 crossrefType "posted-content" @default.
- W3094319733 hasAuthorship W3094319733A5018175815 @default.
- W3094319733 hasAuthorship W3094319733A5034483183 @default.
- W3094319733 hasAuthorship W3094319733A5045198205 @default.
- W3094319733 hasAuthorship W3094319733A5046597133 @default.
- W3094319733 hasAuthorship W3094319733A5061642756 @default.
- W3094319733 hasAuthorship W3094319733A5072326707 @default.
- W3094319733 hasConcept C104317684 @default.
- W3094319733 hasConcept C119857082 @default.
- W3094319733 hasConcept C126255220 @default.
- W3094319733 hasConcept C134306372 @default.
- W3094319733 hasConcept C154945302 @default.
- W3094319733 hasConcept C185592680 @default.
- W3094319733 hasConcept C33923547 @default.
- W3094319733 hasConcept C41008148 @default.
- W3094319733 hasConcept C55493867 @default.
- W3094319733 hasConcept C63479239 @default.
- W3094319733 hasConcept C77553402 @default.
- W3094319733 hasConceptScore W3094319733C104317684 @default.
- W3094319733 hasConceptScore W3094319733C119857082 @default.
- W3094319733 hasConceptScore W3094319733C126255220 @default.
- W3094319733 hasConceptScore W3094319733C134306372 @default.
- W3094319733 hasConceptScore W3094319733C154945302 @default.
- W3094319733 hasConceptScore W3094319733C185592680 @default.
- W3094319733 hasConceptScore W3094319733C33923547 @default.
- W3094319733 hasConceptScore W3094319733C41008148 @default.
- W3094319733 hasConceptScore W3094319733C55493867 @default.
- W3094319733 hasConceptScore W3094319733C63479239 @default.
- W3094319733 hasConceptScore W3094319733C77553402 @default.
- W3094319733 hasLocation W30943197331 @default.
- W3094319733 hasOpenAccess W3094319733 @default.
- W3094319733 hasPrimaryLocation W30943197331 @default.
- W3094319733 hasRelatedWork W2395317528 @default.
- W3094319733 hasRelatedWork W2897959453 @default.
- W3094319733 hasRelatedWork W2962756933 @default.
- W3094319733 hasRelatedWork W2964540166 @default.
- W3094319733 hasRelatedWork W2979999556 @default.
- W3094319733 hasRelatedWork W2981817257 @default.
- W3094319733 hasRelatedWork W2982615324 @default.
- W3094319733 hasRelatedWork W2987875759 @default.
- W3094319733 hasRelatedWork W3019321885 @default.
- W3094319733 hasRelatedWork W3028763319 @default.
- W3094319733 hasRelatedWork W3033323705 @default.
- W3094319733 hasRelatedWork W3035168486 @default.
- W3094319733 hasRelatedWork W3089774673 @default.
- W3094319733 hasRelatedWork W3091918696 @default.
- W3094319733 hasRelatedWork W3128448405 @default.
- W3094319733 hasRelatedWork W3135151133 @default.
- W3094319733 hasRelatedWork W3168586460 @default.
- W3094319733 hasRelatedWork W3169425223 @default.
- W3094319733 hasRelatedWork W3175117184 @default.
- W3094319733 hasRelatedWork W3190398575 @default.
- W3094319733 isParatext "false" @default.
- W3094319733 isRetracted "false" @default.
- W3094319733 magId "3094319733" @default.
- W3094319733 workType "article" @default.