Matches in SemOpenAlex for { <https://semopenalex.org/work/W3207613384> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W3207613384 abstract "Deep Learning (DL) is the force behind the success of solving many complicated tasks in recent years. With the use of DL systems in safety-critical applications, it has become of great importance to make these systems robust against adversarial attacks. Adversarial data generation is an effective tool to make DL systems robust against such attacks, with the help of adversarial training. Recent studies focus on gradient-based adversarial attacks. Although they can successfully generate adversarial samples, high computation cost and lack of flexibility over input generation arise the need for an efficient and flexible adversarial attack methodology. In this paper, we present DeepCustom, a fast and customizable adversarial data generation framework towards bridging this gap. Convolutional autoencoders with custom loss functions, enable user-configurable data generation within a much shorter time compared to the state-of-the-art attack method called PGD. Experiments show that our technique produces adversarial samples faster than PGD and using these samples in adversarial training, allows comparable robustness against adversarial attacks." @default.
- W3207613384 created "2021-10-25" @default.
- W3207613384 creator A5019828883 @default.
- W3207613384 creator A5050136674 @default.
- W3207613384 date "2021-08-01" @default.
- W3207613384 modified "2023-09-27" @default.
- W3207613384 title "Improving Robustness of Deep Learning Systems with Fast and Customizable Adversarial Data Generation" @default.
- W3207613384 cites W2195388612 @default.
- W3207613384 cites W2963207607 @default.
- W3207613384 cites W2964153729 @default.
- W3207613384 cites W2964253222 @default.
- W3207613384 doi "https://doi.org/10.1109/aitest52744.2021.00017" @default.
- W3207613384 hasPublicationYear "2021" @default.
- W3207613384 type Work @default.
- W3207613384 sameAs 3207613384 @default.
- W3207613384 citedByCount "0" @default.
- W3207613384 crossrefType "proceedings-article" @default.
- W3207613384 hasAuthorship W3207613384A5019828883 @default.
- W3207613384 hasAuthorship W3207613384A5050136674 @default.
- W3207613384 hasConcept C104317684 @default.
- W3207613384 hasConcept C105795698 @default.
- W3207613384 hasConcept C108583219 @default.
- W3207613384 hasConcept C113775141 @default.
- W3207613384 hasConcept C11413529 @default.
- W3207613384 hasConcept C119857082 @default.
- W3207613384 hasConcept C154945302 @default.
- W3207613384 hasConcept C174348530 @default.
- W3207613384 hasConcept C185592680 @default.
- W3207613384 hasConcept C2780598303 @default.
- W3207613384 hasConcept C33923547 @default.
- W3207613384 hasConcept C37736160 @default.
- W3207613384 hasConcept C38652104 @default.
- W3207613384 hasConcept C41008148 @default.
- W3207613384 hasConcept C45374587 @default.
- W3207613384 hasConcept C55493867 @default.
- W3207613384 hasConcept C63479239 @default.
- W3207613384 hasConceptScore W3207613384C104317684 @default.
- W3207613384 hasConceptScore W3207613384C105795698 @default.
- W3207613384 hasConceptScore W3207613384C108583219 @default.
- W3207613384 hasConceptScore W3207613384C113775141 @default.
- W3207613384 hasConceptScore W3207613384C11413529 @default.
- W3207613384 hasConceptScore W3207613384C119857082 @default.
- W3207613384 hasConceptScore W3207613384C154945302 @default.
- W3207613384 hasConceptScore W3207613384C174348530 @default.
- W3207613384 hasConceptScore W3207613384C185592680 @default.
- W3207613384 hasConceptScore W3207613384C2780598303 @default.
- W3207613384 hasConceptScore W3207613384C33923547 @default.
- W3207613384 hasConceptScore W3207613384C37736160 @default.
- W3207613384 hasConceptScore W3207613384C38652104 @default.
- W3207613384 hasConceptScore W3207613384C41008148 @default.
- W3207613384 hasConceptScore W3207613384C45374587 @default.
- W3207613384 hasConceptScore W3207613384C55493867 @default.
- W3207613384 hasConceptScore W3207613384C63479239 @default.
- W3207613384 hasFunder F4320306087 @default.
- W3207613384 hasLocation W32076133841 @default.
- W3207613384 hasOpenAccess W3207613384 @default.
- W3207613384 hasPrimaryLocation W32076133841 @default.
- W3207613384 hasRelatedWork W2952919291 @default.
- W3207613384 hasRelatedWork W3193857078 @default.
- W3207613384 hasRelatedWork W3208304128 @default.
- W3207613384 hasRelatedWork W4221150850 @default.
- W3207613384 hasRelatedWork W4223943233 @default.
- W3207613384 hasRelatedWork W4224952001 @default.
- W3207613384 hasRelatedWork W4309045103 @default.
- W3207613384 hasRelatedWork W4312200629 @default.
- W3207613384 hasRelatedWork W4360585206 @default.
- W3207613384 hasRelatedWork W4364306694 @default.
- W3207613384 isParatext "false" @default.
- W3207613384 isRetracted "false" @default.
- W3207613384 magId "3207613384" @default.
- W3207613384 workType "article" @default.