FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2968876075> ?p ?o ?g. }

• W2968876075 abstract "Modern deep neural networks are often vulnerable to adversarial samples. Based on the first optimization-based attacking method, many following methods are proposed to improve the attacking performance and speed. Recently, generation-based methods have received much attention since they directly use feed-forward networks to generate the adversarial samples, which avoid the time-consuming iterative attacking procedure in optimization-based and gradient-based methods. However, current generation-based methods are only able to attack one specific target (category) within one model, thus making them not applicable to real classification systems that often have hundreds/thousands of categories. In this paper, we propose the first Multi-target Adversarial Network (MAN), which can generate multi-target adversarial samples with a single model. By incorporating the specified category information into the intermediate features, it can attack any category of the target classification model during runtime. Experiments show that the proposed MAN can produce stronger attack results and also have better transferability than previous state-of-the-art methods in both multi-target attack task and single-target attack task. We further use the adversarial samples generated by our MAN to improve the robustness of the classification model. It can also achieve better classification accuracy than other methods when attacked by various methods." @default.
• W2968876075 created "2019-08-22" @default.
• W2968876075 creator A5003608795 @default.
• W2968876075 creator A5014963018 @default.
• W2968876075 creator A5029523095 @default.
• W2968876075 creator A5055238399 @default.
• W2968876075 creator A5055760200 @default.
• W2968876075 creator A5064573190 @default.
• W2968876075 creator A5075158591 @default.
• W2968876075 creator A5079410647 @default.
• W2968876075 date "2019-08-14" @default.
• W2968876075 modified "2023-09-26" @default.
• W2968876075 title "Once a MAN: Towards Multi-Target Attack via Learning Multi-Target Adversarial Network Once" @default.
• W2968876075 cites W1522301498 @default.
• W2968876075 cites W1536680647 @default.
• W2968876075 cites W1665214252 @default.
• W2968876075 cites W1686810756 @default.
• W2968876075 cites W1883420340 @default.
• W2968876075 cites W1932198206 @default.
• W2968876075 cites W2077658674 @default.
• W2968876075 cites W2108598243 @default.
• W2968876075 cites W2145287260 @default.
• W2968876075 cites W2194775991 @default.
• W2968876075 cites W2243397390 @default.
• W2968876075 cites W2460937040 @default.
• W2968876075 cites W2565639579 @default.
• W2968876075 cites W2603766943 @default.
• W2968876075 cites W2604147826 @default.
• W2968876075 cites W2612372205 @default.
• W2968876075 cites W2613904329 @default.
• W2968876075 cites W2620038827 @default.
• W2968876075 cites W2693668331 @default.
• W2968876075 cites W2752782242 @default.
• W2968876075 cites W2775424324 @default.
• W2968876075 cites W2783555701 @default.
• W2968876075 cites W2950906520 @default.
• W2968876075 cites W2952678275 @default.
• W2968876075 cites W2953106684 @default.
• W2968876075 cites W2963207607 @default.
• W2968876075 cites W2963389226 @default.
• W2968876075 cites W2963403868 @default.
• W2968876075 cites W2963857521 @default.
• W2968876075 cites W2964153729 @default.
• W2968876075 cites W3103557498 @default.
• W2968876075 cites W3118608800 @default.
• W2968876075 doi "https://doi.org/10.48550/arxiv.1908.05185" @default.
• W2968876075 hasPublicationYear "2019" @default.
• W2968876075 type Work @default.
• W2968876075 sameAs 2968876075 @default.
• W2968876075 citedByCount "1" @default.
• W2968876075 countsByYear W29688760752020 @default.
• W2968876075 crossrefType "posted-content" @default.
• W2968876075 hasAuthorship W2968876075A5003608795 @default.
• W2968876075 hasAuthorship W2968876075A5014963018 @default.
• W2968876075 hasAuthorship W2968876075A5029523095 @default.
• W2968876075 hasAuthorship W2968876075A5055238399 @default.
• W2968876075 hasAuthorship W2968876075A5055760200 @default.
• W2968876075 hasAuthorship W2968876075A5064573190 @default.
• W2968876075 hasAuthorship W2968876075A5075158591 @default.
• W2968876075 hasAuthorship W2968876075A5079410647 @default.
• W2968876075 hasBestOaLocation W29688760751 @default.
• W2968876075 hasConcept C104317684 @default.
• W2968876075 hasConcept C119857082 @default.
• W2968876075 hasConcept C127413603 @default.
• W2968876075 hasConcept C140331021 @default.
• W2968876075 hasConcept C154945302 @default.
• W2968876075 hasConcept C185592680 @default.
• W2968876075 hasConcept C201995342 @default.
• W2968876075 hasConcept C2780451532 @default.
• W2968876075 hasConcept C2984842247 @default.
• W2968876075 hasConcept C37736160 @default.
• W2968876075 hasConcept C41008148 @default.
• W2968876075 hasConcept C50644808 @default.
• W2968876075 hasConcept C55493867 @default.
• W2968876075 hasConcept C61272859 @default.
• W2968876075 hasConcept C63479239 @default.
• W2968876075 hasConceptScore W2968876075C104317684 @default.
• W2968876075 hasConceptScore W2968876075C119857082 @default.
• W2968876075 hasConceptScore W2968876075C127413603 @default.
• W2968876075 hasConceptScore W2968876075C140331021 @default.
• W2968876075 hasConceptScore W2968876075C154945302 @default.
• W2968876075 hasConceptScore W2968876075C185592680 @default.
• W2968876075 hasConceptScore W2968876075C201995342 @default.
• W2968876075 hasConceptScore W2968876075C2780451532 @default.
• W2968876075 hasConceptScore W2968876075C2984842247 @default.
• W2968876075 hasConceptScore W2968876075C37736160 @default.
• W2968876075 hasConceptScore W2968876075C41008148 @default.
• W2968876075 hasConceptScore W2968876075C50644808 @default.
• W2968876075 hasConceptScore W2968876075C55493867 @default.
• W2968876075 hasConceptScore W2968876075C61272859 @default.
• W2968876075 hasConceptScore W2968876075C63479239 @default.
• W2968876075 hasLocation W29688760751 @default.
• W2968876075 hasOpenAccess W2968876075 @default.
• W2968876075 hasPrimaryLocation W29688760751 @default.
• W2968876075 hasRelatedWork W2911510572 @default.
• W2968876075 hasRelatedWork W2952919291 @default.
• W2968876075 hasRelatedWork W2963857521 @default.
• W2968876075 hasRelatedWork W3185166384 @default.
• W2968876075 hasRelatedWork W3193857078 @default.
• W2968876075 hasRelatedWork W3208304128 @default.

• next